Virtual production and spatial media

Real-time scenes, cameras, capture, XR, volumetric and spatial storytelling

• articleDoes hdPrman always convert USD Gaussian-splat ParticleField prims to RenderMan points? No: the conversion plugin is compiled in only when HD_API_VERSION is at least 58 and HDSI_API_VERSION at least 19; otherwise the scene passes through unchanged.
  Problem. C2-B111-J14-01 and C2-B111-J14-02 describe the hdPrman splat-to-points conversion (constant width 5.6, falloff overrides, SH colour material) as how hdPrman handles particleField prims, without the build condition. Conditions. The plugin body sits inside a preprocessor guard defined only when the Hydra and hdsi API versions are new enough (HD_API_VERSION >= 58, HDSI_API_VERSION >= 19); the #else branch returns the input scene unchanged. Method. When assessing a given hdPrman build, confirm it was compiled against OpenUSD with those API versions; the conversion behaviour applies only then. Failure modes. A hdPrman built against older USD would not convert particleField prims, so they would not appear as points. Limitations. The file is identical in v26.08, v26.11.0, v26.11.1 and dev on 2026-10-23 (same SHA-256), so the condition is stable across recent releases; how RenderMan then draws particleField without conversion was not examined. The overrides values (ri:falloffshape ...
• articleIn OpenXR 1.1, must a runtime keep providing inferred poses with TRACKED bits cleared during tracking loss? Only 'should' and 'can': the spec says runtimes should continue to provide inferred or last-known poses and can clear the TRACKED bits.
  Problem. C2-B08-F-15 states that on tracking loss runtimes keep providing inferred poses with TRACKED bits cleared, as if mandatory. Conditions. LOCAL (and STAGE) reference spaces in OpenXR 1.1.65. Method. Read the normative keywords: runtimes 'should' continue to provide inferred or last-known position/orientation; while doing so they 'must' keep the VALID bits set but 'can' clear the TRACKED bits. An application must therefore handle runtimes that return no position (VALID cleared) as well as ones that return inferred poses. Failure modes. Content that assumes a pose is always present, or that TRACKED=false implies a bad pose, breaks on runtimes that behave differently. Limitations. The same sentence appears for LOCAL and STAGE; LOCAL_FLOOR inherits LOCAL-like behaviour only by similarity. Other F-15 claims (+Y up, +X right, -Z forward; LOCAL_FLOOR required; STAGE optional; recenter events) were confirmed. Version/date. Spec 1.1.65, fetched 2026-10-23.
• articleHow does spatial audio for XR/immersive delivery (ASAF/APAC, IAMF, MPEG-H, OpenXR) differ in role and scope from the cinema/broadcast Audio Definition Model (ITU-R BS.2076-3)?
  Partially verified: the curator re-read S14, S18, S2; S13, S15 were not re-read by the curator and rest on the producer's pinned reading. ADM (ITU-R BS.2076-3, 2025) describes audio rather than carrying it: channels are typed DirectSpeakers, Matrix, Objects, HOA or Binaural, with head-locked and headphone-virtualise parameters, and the audio travels in BW64 with rendering left to a separate renderer. Apple's ASAF, by contrast, packages metadata with linear PCM in Broadcast Wave and depends on Apple's built-in renderer, which adapts to object and listener position and orientation; it is streamed as APAC. The Apple talk does not mention ADM, and no inspected source documents converting an ADM master to ASAF. IAMF combines audio elements and mix presentations for device-specific rendering.
• articleFor ambisonic (HOA) audio in immersive delivery, what orders, channel ordering/normalisation, bitrates and listener-motion behaviour do Apple APAC, IAMF, OpenXR's BD extension, glTF MPEG_audio_spatial and ADM specify?
  Partially verified: the curator re-read S11, S14, S3; S13, S15, S18, S2 were not re-read by the curator and rest on the producer's pinned reading. Ambisonic conventions differ by delivery format: Apple's built-in APAC encoder takes 1st-3rd order (384-768 kbps recommended) without naming a normalisation in the session; IAMF fixes AmbiX (ACN order, SN3D) with (n+1)^2 channels up to order 14 in mono or projection mode; glTF MPEG_audio_spatial renders HOA sources at the listener with head rotation only (3DoF). State order, ordering and normalisation explicitly when moving material between them.
• articleWhich spatial-audio formats and APIs do public XR and immersive-delivery documents actually define (Apple ASAF/APAC, IAMF, MPEG-H, glTF MPEG_audio_spatial, OpenXR, WebXR, Web Audio), and where is there nothing to read?
  Partially verified: the curator re-read S2; S11, S13, S14, S15, S16, S17 were not re-read by the curator and rest on the producer's pinned reading. Spatial audio is defined at different layers: Apple uses ASAF for production and the APAC codec for delivery (APAC required for Apple Immersive Video); AOMedia's IAMF is an open model and container for channel, ambisonic and object audio with binaural rendering signals; WebXR defines no audio of its own (web apps rely on Web Audio). No single open format spans production, delivery and XR playback in the documents read.
• articleHow does Apple say 180, 360 and wide-FOV (fisheye) video is signalled in QuickTime/MP4 for APMP, converted from Google Spherical Video tags, streamed with HLS, and played back in visionOS?
  Partially verified: the curator re-read S3; S4 was not re-read by the curator and rests on the producer's pinned reading. In Apple's Projected Media Profile the projection kind is the discriminator (rectilinear for 2D/3D/spatial, half-equirectangular for 180, equirectangular for 360, parametric for wide-FOV); HLS publishing declares stereo and projection in REQ-VIDEO-LAYOUT and the init map segment must repeat the format information.
• articleWhich results from planning-with-a-learned-model papers could transfer to media or agent workflows, and which are specific to robotics or games?
  In the inspected papers the demonstrated uses are games, simulated control and robot manipulation; none reports a media-production or LLM-agent workflow. What may transfer is method-level (plan by sampling sequences through a learned predictor, check model exploitation by comparing virtual versus real score, use a latent rather than pixel predictor for speed) not the results. Specifically, V-JEPA 2-AC needed a goal image and a reward-free robot dataset; Dreamer and TD-MPC2 need reward signals; the exploit-the-dream failure from 2018 is the most portable lesson. This is a synthesis; no experiment was run.
• articleBeginner: what minimum evidence should an agent require before telling a production that a world model 'worked' on a job, and which found cases meet it?
  PROPOSAL (synthesis, not a tested standard): require eight items before saying a world model worked on a job: system and version, production date, task, inputs, outputs used in the final cut, a comparison baseline that was actually run, who measured and who wrote the claim, and what was not measured. Mapping the cases found: none of the generative cases meets items 1, 5 or 6; the only case with a run alternative (DOSENMUTTER) is not a world-model case. Until a case meets the checklist, an agent should say 'vendor reports' and not 'it worked'.
• articleWhat acceptance check could an agent run before relying on a streaming video or world model for a long take (proposal, not a tested protocol)?
  No source gives a ready acceptance test. Combining measures the papers use gives a proposal: generate at the longest length you need, score per-segment brightness/imaging quality and a motion measure, compute first-vs-last delta, run a copy-first-clip control, and separately test whether the model returns to an earlier place (memory), which the papers say these methods do not provide. This is synthesis, untested.
• articleHow do I mark an MP4 or WebM as 360, VR180 or stereoscopic so YouTube and players treat it correctly, and which stereo layouts are defined?
  Partially verified: the curator re-read S9; S11, S4, S5 were not re-read by the curator and rest on the producer's pinned reading. Spherical Video V2 puts projection metadata in sv3d (svhd, proj with cbmp/equi/mshp) and stereo layout in st3d on the video sample entry, with WebM equivalents; V1 and V2 may coexist and V2 wins when they differ. YouTube's help names only left-right stereo for 3D (producer reading), while the RFC defines more stereo modes.
• articleWhat do the Unreal Engine 5.8 Movie Render Queue/Graph docs say about temporal sampling, warm-up frames, frame-rate override and audio output for offline capture?
  Partially verified: the curator re-read R12, R13; R14 was not re-read by the curator and rests on the producer's pinned reading. Unreal MRQ guidance uses render and engine warm-up counts (120 each in the guide) to build temporal history before output, supports .wav audio output, and uses temporal samples (sub-frame) for anti-aliasing/motion blur; exact temporal-sampling prose was not re-read by the curator.
• articleWhat do Unity Recorder 5.1.7 and Time.captureFramerate document about constant versus variable frame rate capture, audio capture and determinism?
  Partially verified: the curator re-read R5, R6; R10, R11, R7, R8, R9 were not re-read by the curator and rest on the producer's pinned reading. Unity Recorder offers Constant playback (fixed interval between recorded frames, recommended for non-interactive content) and Variable playback (game-view timing); Time.captureDeltaTime advances game time at a fixed interval regardless of real time. The docs read do not state that Constant mode uses captureDeltaTime (producer note kept).
• articleIf I author projectionModeHint or sortingModeHint on a USD gaussian splat, will it change how the Pixar-shipped renderers draw it?
  Partially verified: the curator re-read S1, S5; S6, S7, S8 were not re-read by the curator and rest on the producer's pinned reading. At v26.11.1 nothing changes from v26.11.0 in the files read: hints are passed to Hydra but the sample splat renderer still sorts by view-space depth. Treat the hints as metadata for other renderers, not as a control of look or correctness in Pixar's in-repo code.
• articleWhat does the public MPEG V-PCC/V3C reference software (mpeg-pcc-tmc2 release-v25.0) say about its role, build dependencies, how occupancy, geometry and attribute video are encoded, and under what licence?
  MPEG's V-PCC reference software (TMC2, release-v25.0) is an experimental reference, not an efficient implementation: it codes a point cloud as separate occupancy, geometry and attribute 2D video streams using external video codecs selected by codecId (JM, HM, VTM, SHM, or FFmpeg on a branch), with stacked configuration files where later files override earlier ones; its test example expects an external MPEG dataset path. The code is under an ISO/IEC BSD-style licence that expressly grants no patent rights, so patent clearance is a separate question.
• articleHow much do pixels differ across GPUs and browsers for the same WebGL or WebGPU scene, and what tolerance do conformance tests allow?
  A 2012 study rendered one simple antialiased WebGL scene on 270 crowd-sourced machines: the images looked identical but formed 50 distinct pixel-level renders, mostly consistent within a graphics-card model (the text also mentions 51 groups). Current WebGPU conformance tests assume small differences: integer formats compare exactly by default, float and normalised formats can use ULP or fractional thresholds, a canvas colour-space reftest allows up to 2 levels per channel, and WGSL leaves the rounding mode open when quantising. So pixel-exact equality across devices should not be expected; no recent cross-device measurement was found.
• articleWhat do the NVIDIA Cosmos paper and docs actually document for synthetic data generation and agent evaluation, versus only propose?
  Partially verified: the curator re-read none of the cited sources; S5, S7, S8, S9 rest on the producer's pinned reading. The Cosmos paper (v3) lists four uses of a world foundation model (policy evaluation, policy initialization/training, planning, synthetic data) and says it reports no empirical results for them. What it does measure are model-level checks: 3D consistency, physics alignment and post-training results for camera control, robotic manipulation (action-conditioned and instruction-conditioned video prediction) and driving. The docs (observed 2026-10-22) describe workflows with inputs/outputs: Cosmos-Transfer2.5 for two augmentation workflows (Simulations to Photorealism; Scale World State Diversity) with computed control maps; Predict2.5 action-conditioned post-training on Bridge end-effector poses; Reason1 best-of-N rejection sampling with a score = fraction of artifact-free evaluations. The docs show example videos and procedures but no downstream policy or accuracy re...
• articleBefore using a generated world (Marble splat or mesh, HunyuanWorld layers, WonderWorld splat) for previs or as an LED-volume background, what should an agent check, what does the one documented LED-volume use report, and what is unknown?
  Partially verified: the curator re-read none of the cited sources; S25, S20, S9, S15, S16, S21, S5 rest on the producer's pinned reading. The only documented LED-volume use found is a vendor case study (Volinga, Feb 2026): a music video used Marble worlds shown as Gaussian splats in Unreal via the Volinga plugin, with stYpe camera tracking and set extension; the vendor and its customer report time saved and on-set switching, with no data on colour, resolution, latency or artifacts. World Labs' docs add plugin notes for nDisplay and depth of field. WonderWorld's authors say its own results have low density and floaters and suggest it as a coarse prototype to refine. The checks below are proposals synthesised from these statements, not tested procedures.
• articleWhich benchmark checks whether a video or world-generation model follows a camera path and keeps a scene consistent, and does it measure physical laws?
  Partially verified: the curator re-read none of the cited sources; S3, S10, S11 rest on the producer's pinned reading. WorldScore (Stanford; arXiv v2 Nov 2025) evaluates 'next scene' generation: given a scene image, a next-scene prompt and a camera layout (a trajectory plus one of 8 text camera moves), it scores controllability (camera, object, content), quality (3D, style, photometric consistency, subjective quality) and dynamics (motion accuracy, magnitude, smoothness). It tested 20 models, including 13 video models; video models had weak camera control (best video 40.22 on camera controllability) and 3D scene generators beat them on static worlds. It does not define a physical-law metric, so it informs camera and consistency questions only.
• articleWhat exactly does HunyuanWorld 1.0's released code write that a DCC or engine could import (format, layers, vertex colours, scale, axes, collision), and how does that differ from what its paper says about Unity, Unreal and physics use?
  Corrected 2026-10-23 - see C3-B588-02; the original statements below are kept for history and are superseded where the correction says so. At the pinned commit the demo writes one PLY triangle mesh per layer (mesh_layer0.ply, ...; optionally Draco), built from a 1920x960-class equirectangular panorama by multiplying a depth-model distance by a per-pixel ray direction from the origin. Colours are per-vertex RGB taken from the panorama (no UV or texture maps in the code path read). Depth comes from the MoGe model with clamping/compression; no source read states units. No collider or engine-specific export is written. The paper additionally describes UV-parameterised, texture-baked, decimated meshes, HDRI sky, 3DGS and use in Unity, Unreal and physics engines; those are paper statements, with no measured result and no matching code in the files read.
• articleWhat do World Labs' docs state about Marble exports entering a DCC, engine or virtual-production pipeline: file formats, units and scale, coordinate convention, baked vs dynamic lighting, and collision?
  Corrected 2026-10-23 - see C3-B598-02; the original statements below are kept for history and are superseded where the correction says so. Marble exports splats (PLY, SPZ) and GLB meshes. Docs state: splats need third-party plugins in Unreal, Unity, Blender and Houdini; collider meshes (100-200k triangles) are for coarse physics, not visual rendering; units are 'arbitrary model units' in API exports, with a metric_scale_factor and ground_plane_offset supplied for conversion; and the coordinate convention is documented inconsistently across pages and dates (OpenCV-style 'raw' for SPZ, OpenGL default from Dec 2025, an OpenGL/OpenCV option from Jan 2026). No inspected page says whether lighting is baked into splat colours; plugin pages describe relighting and shadows as plugin-dependent.
• articleWhich of the driving and robot world models can an agent actually download and run, on what hardware, and what does each component's text say?
  Corrected 2026-10-23 - see C3-B598-04; the original statements below are kept for history and are superseded where the correction says so. Open and runnable: Vista (weights on Hugging Face, 32 GB VRAM for sampling), Cosmos-Predict1 driving multi-view checkpoints (three types in the downloader) and Cosmos-Predict2.5 driving multiview and robot action-conditioned models (README/table listed), and the 1X challenge GENIE baselines. Code only: DriveDreamer (research code; no weights named in README/DOCS). Not found: GAIA-1/2/3/4 (no repository, release or access statement found) and 1XWM (no release stated). Hardware is large for the Cosmos multiview models (8 GPUs of 80 GB for Predict2.5 multiview inference). Rights differ per component and there is one same-work tension: Vista's card says Apache-2.0 while its paper says it was initialised from SVD, whose checkpoint the authors call non-commercial. Cosmos licence clauses are covered by C3-B019-W6 and are not repeated.
• articleIf I have one video (or one image) of an object and no rig, which video-to-4D generation systems can produce an animated 3D object, what do they output, and what do they cost to run?
  Corrected 2026-10-23 - see C3-B588-09; the original statements below are kept for history and are superseded where the correction says so. Four released video-to-4D lines were read at pinned versions. Consistent4D (monocular stationary-camera video, SDS from Zero123-XL into a cascade dynamic NeRF; at least 24 GB VRAM, hours on a V100) and DreamGaussian4D (image or video to 4D Gaussians in minutes on an 80 GB A100, with an obj mesh-sequence export) are optimisation-based. SV4D and SV4D 2.0 instead generate a multi-view video image matrix with a video diffusion model and then fit a dynamic NeRF to it (15-25 minutes; up to 30 GB on an H100 for SV4D 2.0). All are object-centric; SV4D 2.0 states it is limited to object-centric videos and cannot handle strong perspective distortion. Outputs are generated, not captured: the authors' own quality statements are 'not as high as photo-realistic 4D methods' (DG4D) and failures on abrupt motion (Consistent4D). Weights and rights are in candidate...
• articleWhat representation does each of Marble, HunyuanWorld 1.0, WonderWorld and WonderJourney actually output (splats, meshes, panoramas, depth layers, point clouds, video), and is each a paper result, a demo or a released capability?
  Corrected 2026-10-23 - see C3-B588-01 and C3-B598-01; the original statements below are kept for history and are superseded where the correction says so. The four systems output different things. Marble (World Labs) is a hosted product whose docs list Gaussian splats (SPZ/PLY), triangle meshes (GLB), a 360 panorama and rendered video. HunyuanWorld 1.0 builds layered meshes from a generated panorama plus depth; its paper also describes a 3DGS and an HDRI-sky option, but the released demo code at the pinned commit writes only per-layer vertex-coloured PLY meshes (optional Draco). WonderWorld produces Fast Gaussian Surfels (saved as .ply and .splat by its code); WonderJourney produces a sequence of coloured point clouds that its code renders to video. RTFM, also from World Labs, deliberately has no explicit 3D representation. Labels differ by component, see systems[].
• articleWhat licences and access terms apply to Marble, HunyuanWorld 1.0, WonderWorld and WonderJourney (code, weights, outputs), and what hardware does running each require?
  Corrected 2026-10-23 - see C3-B588-03; the original statements below are kept for history and are superseded where the correction says so. Four different regimes. Marble is a hosted service under World Labs Terms of Service (last updated 2026-01-21): Free-account output is retained by World Labs with a personal non-commercial licence to the user; paid-account output is owned by the user including commercial purposes, with a training licence over user content that paid users may opt out of. HunyuanWorld 1.0 is under a Tencent community licence that is expressly limited to a Territory excluding the EU, UK and South Korea, includes a 1M monthly-active-user trigger and a bar on using outputs to improve other AI models. WonderJourney code is MIT. WonderWorld has no licence file at the pinned commit. Nothing here is legal clearance.
• articleWhich primary pages support the Vista (32 GB, Apache-2.0) and Cosmos-Predict2.5 multiview (8x80 GB) hardware and licence statements previously cited only to the Apache licence text?
  Correction to C3-B144-W29-05 (nature: citation does not support the claims; facts hold at other primary pages). Original summary cites only the generic Apache-2.0 text, which cannot support product-specific claims on hardware, weights or availability. Audit result: Vista's SAMPLING.md suggests GPUs with a minimum of 32 GB VRAM for sampling (with a --low_vram option for GPUs under 80 GB); Cosmos-Predict2.5's multiview inference guide requires at least 8 GPUs with 80 GB each; Vista's README states its repository content is under Apache-2.0 and the Hugging Face model record tags apache-2.0. The 'not found' claims for GAIA, DriveDreamer weights and 1XWM, and the Vista-versus-SVD licence tension, were not re-verified. Replace the single Apache URL with these pages when citing. Version/date: fetched 2026-10-23.
• articleWhat do World Labs' current docs say about Marble units and default coordinate convention, and does the 'arbitrary model units' / 'OpenGL default from Dec 2025' wording hold on the cited pages?
  Correction to C3-B012-W4-05 (nature: changed or unsupported on the cited pages). Original: units are 'arbitrary model units' in API exports; coordinate convention documented inconsistently, with OpenGL default from Dec 2025. Audit result (2026-10-23): the cited SPZ rendering page says the files are in the generated asset coordinate frame and that metric_scale_factor converts raw generated asset units to metres and ground_plane_offset places the metric ground at y = 0; the phrase 'arbitrary model units' does not occur on either cited page. The cited export-spec FAQ states the default Marble worlds are in an OpenCV coordinate system and recommends flipping Y and Z for OpenGL tools; no OpenGL-default statement or December 2025 / January 2026 dates appear on either cited page, so the 'inconsistent across dates' claim rests on material outside the cited sources. Agents should apply the scale metadata (metres) and the OpenCV-to-OpenGL flip as documented now, and re-check if a changelog is...
• articleWhat does World Labs' Marble export-spec page actually list (panorama size, mesh tiers and their limits), and is video part of that list?
  Correction to C3-B012-W4-01 (nature: missing limitation; one item not on the cited page). Original: the docs list splats, GLB meshes, a 360 panorama and rendered video. Audit result: the cited export-spec page (checked 2026-10-23) lists a prompt image, a 2560x1280 equirectangular PNG panorama, SPZ and PLY splats at about 2M and 500k, a coarse collider GLB (100-200k triangles) and a high-quality mesh tier. The high-quality tier is two GLBs (about 600k triangles with texture, about 1M with vertex colours), takes up to an hour, is rate limited to 4 generation requests per hour per user and only for worlds the user owns; the original omitted these limits. The export-spec page does not mention video. Video appears in the docs index as a studio Record tool for flythrough videos, a different feature from export files, so 'rendered video' should be attributed to Record, not the export specs. Version/date: docs as fetched 2026-10-23.
• articleWhat licence applies to the StereoCrafter code and weights, and can I use them commercially?
  Correction (changed or newly resolved). C3-B581-06 (round 3) said the StereoCrafter licence file was not found on the repository main branch, so reuse rights were unverified. The Hugging Face model repository for TencentARC/StereoCrafter carries a LICENSE and a NOTICE. The LICENSE states the project is fine-tuned with the assistance of Stable Video Diffusion, which is under a Non-Commercial Community License, and adds that users agree to use StereoCrafter only for academic, research and education purposes, refraining from any commercial or production purposes. The NOTICE lists the Stable Video Diffusion model as a third-party component under its own licence. So StereoCrafter is non-commercial; do not use it to produce client or production stereo conversions. Limitations. The GitHub main branch still returned 404 for LICENSE, LICENSE.md and LICENSE.txt, so the licence text was read from the Hugging Face repository. Version/date. Fetched 2026-10-23; HF model last modified 2024-12-27.
• articleWhat resolution does HunyuanWorld 1.0's world_composer use by default, and is it 1920x960?
  Correction (changed or unsupported figure). C3-B012-W4-06 says the demo builds meshes from a '1920x960-class' equirectangular panorama. In the pinned world_composer.py the default working resolution is 3840 x 1920 (width, height), the foreground and background mesh resolution caps are 3840, and only the sky mesh cap is 1920. Input panoramas of another size are resized to the configured resolution. The 1920x960 figure is therefore not what the cited file defines, though the 2:1 aspect is right. Version/date. Pinned commit 57fa9f3 fetched 2026-10-23.
• articleWhich Marble exports are documented at the cited pages, and what does HunyuanWorld 1.0's pinned README say it outputs (is video or 3DGS/HDRI documented there)?
  Correction (unsupported by the cited source). C3-B012-W4-01 says Marble's cited docs list rendered video as an export and that the HunyuanWorld paper describes 3DGS and an HDRI sky. Re-fetch 2026-10-23: the cited export specs page lists a 360 panorama (equirectangular 2560 x 1280 png), SPZ/PLY splats and GLB meshes, with no video file among them; video appears only in the plan page, where Pro adds 'enhancing the quality of generated video outputs'. The pinned HunyuanWorld README describes panoramic world proxies and a layered mesh with mesh export; it does not mention 3DGS or an HDRI sky (the paper, which was not among the cited URLs, may). Use the narrower statement unless a cited page is added. Limitations. Video generation is a documented Marble feature; only a video export format is unsupported at the cited page. Version/date. Fetched 2026-10-23.
• articleAt camdkit 0362321d the OpenTrackIO protocol version constant is 1.0.1 (the only GitHub release is v1.0.0 per producer, so pin the commit); pose rotation is intrinsic ZXY Euler in degrees with Y forward, which differs from USD/glTF axis...
  At camdkit 0362321d the OpenTrackIO protocol version constant is 1.0.1 (the only GitHub release is v1.0.0 per producer, so pin the commit); pose rotation is intrinsic ZXY Euler in degrees with Y forward, which differs from USD/glTF axis conventions.
• articleThe camdkit OpenCV-to-OpenTrackIO note maps OpenCV k1..k6 to interleaved OpenTrackIO l-coefficients scaled by F^2, F^4, F^6 (so a naive k-to-l copy is wrong) and records a correction: earlier versions omitted the half-image principal-point term because OpenCV's origin is the top-left...
  The camdkit OpenCV-to-OpenTrackIO note maps OpenCV k1..k6 to interleaved OpenTrackIO l-coefficients scaled by F^2, F^4, F^6 (so a naive k-to-l copy is wrong) and records a correction: earlier versions omitted the half-image principal-point term because OpenCV's origin is the top-left corner.
• articlelibbw64 (d3dae5c7) rejects audioTrackUIDs longer than 12 characters, caps chna UIDs at 1024 and parses only PCM (formatTag 1) or extensible (0xfffe) format headers (static...
  libbw64 (d3dae5c7) rejects audioTrackUIDs longer than 12 characters, caps chna UIDs at 1024 and parses only PCM (formatTag 1) or extensible (0xfffe) format headers (static reading).
• articleglTF 2.0 perspective cameras carry only aspectRatio, yfov, zfar and znear, so converting a physical camera (focal length, apertures, offsets) to glTF keeps only field of view and ratio; recovering focal length from glTF needs sensor size supplied out of...
  glTF 2.0 perspective cameras carry only aspectRatio, yfov, zfar and znear, so converting a physical camera (focal length, apertures, offsets) to glTF keeps only field of view and ratio; recovering focal length from glTF needs sensor size supplied out of band.
• articleHow does a working primary colourist describe balancing, shot matching and contrast in a transcribed talk?
  One post-house colourist describes an order of work for matching: balance each shot, match the balanced shots, then apply the look, while noting the steps overlap in practice and that a well-balanced shot responds better to later keys and colour separation. Matching by piling on keys and windows tends to fall apart or look digital; for a hard match she overshoots the correction and dissolves the node's opacity back, and keeps a prepared node that lowers contrast while raising saturation to hold saturation even. Practitioner testimony from one Resolve-centred colourist, with no numeric method.
• articleField by field, how do the ratified KHR_gaussian_splatting extension and OpenUSD's ParticleField3DGaussianSplat schema define a splat's position, rotation, scale, opacity, spherical harmonics, kernel, projection, sorting, colour space and frame, and where do they differ?
  Both definitions store linear scale and linear 0..1 opacity (CA-B035), but defaults and fields differ: glTF KHR_gaussian_splatting requires a colorSpace string and defaults sortingMethod to cameraDistance, while the OpenUSD usdVol schema defaults sortingModeHint to zDepth and has no colour-space attribute, so a converter that copies defaults changes the declared sort metric and loses colour-space provenance. The glTF README carries an SPDX CC-BY-4.0 header and also a Khronos copyright statement limiting reproduction to the unmodified specification.
• articleWhat are SMPTE ST 2086 mastering-display metadata and CTA-861.3 MaxCLL/MaxFALL, and what can be verified from free public texts?
  SMPTE ST 2086 exists as 2014 and 2018 (stabilized) publications in the SMPTE library, and its text was not read; the free AV1 specification carries the same mastering-display data model (three primaries and white point as 0.16 fixed-point CIE 1931 coordinates, max luminance 24.8 and min luminance 18.14 fixed-point in cd/m2) and defers MaxCLL/MaxFALL definitions to CEA-861.3 Appendix A; FFmpeg stores these as rationals and unsigned cd/m2 values without defining how to measure them.
• articleWhich ADM (BS.2076) versions and profiles does the EBU ADM Renderer accept, what is its licence, and how do BS.2125 serial ADM and BS.2127 relate to it?
  At commit 5bb17b42 the EBU ADM Renderer documents BS.2076-1 as its ADM target and, from v2.0, calls itself the reference implementation of BS.2127; files declaring ADM version 2 or later render with a 'not standardised' warning (preliminary BS.2076-2 support is unreleased), serial ADM (BS.2125) is not mentioned in the README, changelog or render command, and the licence is BSD 3-Clause Clear with an explicit exclusion of patent licences.
• articleWhat is the standing of the WebXR Device API and how do its reference-space types line up with OpenXR's?
  The WebXR Device API at /TR/webxr/ is a W3C Candidate Recommendation Draft dated 9 June 2026 (not a Recommendation) and defines five reference-space types (viewer, local, local-floor, bounded-floor, unbounded) with spatial-tracking consent requirements; OpenXR's spaces chapter (release-1.1.65) uses VIEW, LOCAL, LOCAL_FLOOR and STAGE tokens. Names overlap, but no normative mapping between the two sets is stated in the texts read.
• articleFor first-order Ambisonics, what channel order and per-channel gains convert FuMa/B-format (W,X,Y,Z) to ACN/SN3D (ambiX), according to the ambiX paper and the ambix converter, SAF and SPARTA code?
  ambix (24d2875f) and Spatial_Audio_Framework (18fd5aba) both implement first-order FuMa to ACN/SN3D as a W,X,Y,Z -> W,Y,Z,X reorder with W gain sqrt(2) and unit dipole gains (static code reading; not run). The producer's own caveat that these are not independent (shared authorship lineage with the format paper) is retained.
• articleWhat does Panasonic's AW-UE150 manual document for FreeD output (message type, field mapping, units, ports, client limits, caveats), and what could not be read for Sony?
  The 2025-01 AW-UE150 manual documents FreeD Type D1 output with fixed-zero X/Y/Z, raw zoom/focus ranges 000555h-000FFFh, iris in the 16-bit spare field, Camera ID always FFh, and UDP output to up to four clients (factory ports from 1111).
• articleHow do you "AI-render" a 3D layout locally (3D passes -> video model), and how did the best local approach change from Feb to Aug 2026?
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Three Mickmumpitz videos trace one pipeline across 2026. Feb (V1): Inner-Reflections' VACE + SkyReels V3 R2V merge (Apache-2.0 card) reads control passes (VACE) and reference images (SkyReels); export an outline pass (Blender Workbench flat black + white outlines, or Freestyle as a render pass) and a normalized/inverted Z depth pass with a contrast curve; outlines keep composition but let the model invent detail, depth follows geometry more tightly, blend both if needed; keep control-net strength low for start-frame image generation (Z-Image Turbo + control nets); free workflow ~120 frames at 24 fps; paid version chains 81-frame chunks with 11 overlapping start frames f...
• articleHow can you generate an explorable 3D Gaussian-splat world from one image or prompt locally, and which world-generation approaches failed on consumer hardware (per Mickmumpitz, Aug 2026)?
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Mickmumpitz (2026-08-25) reports weeks of R&D: Apple SHARP (single-image to splat in one pass) stitched across 360-degree slices produced seams and fell apart off-axis, and its licence did not suit commercial users; Insta360 UniSarp (360 to 3D) degrades quickly when moving; HunyuanWorld 2.0 needs two large models resident and targets 4 GPUs; NVIDIA Lyra ran but needs 91 GB of checkpoints, Linux-only, 6-minute first start; World Labs Marble is fast and crisp but restricts movement area and lacks working reflections. Chosen base: Skywork Matrix-3D (MIT): 360 panorama -> depth (MoGe) -> rough mesh -> render camera paths -> Wan 2.1 video model + a lightweight LoRA in-paints...
• articleWhat is the byte layout, scaling and checksum of a FreeD D1 packet, and where do public sources disagree?
  The stvmyr/freeD Go implementation (722d3054) and Vizrt Tracking Hub 1.7 docs both describe the 0x40-minus-byte-sum checksum over a 29-byte D1 packet; the Go code slices eight 3-byte fields at offsets 2-26.
• articleWhat is the FreeD protocol, what camera data can it carry, and what can I not expect from it in a virtual-production setup?
  Vendor documents describe FreeD D1 as carrying camera ID, pan/tilt/roll, X/Y/Z, zoom and focus plus a 16-bit spare field, with no lens-distortion data (producer citations; curator confirmed the spare-field and zero-position usage in the Panasonic manual).
• articleWith eye tracking inside a headset, how often do viewers never look at content placed outside their starting field of view in a 360-degree video, and do arrow cues change that?
  Liu, Xu, Yang, Li and Huang (Frontiers in Psychology 12:792069, CC BY, Europe PMC full text PMC8828640) eye-tracked 110 students (HTC Vive Pro + Tobii Pro VR, 120 Hz) watching a 3 min 24 s 360-degree animated science video in four conditions. Without arrows, 57% of the group whose annotations lay outside the initial field of view had zero fixation on them, and their annotation-area fixation was about half that of the in-view group (6.98 s vs 14.03 s); adding arrows in the initial view restored it (13.64 s, p<0.001 vs the no-arrow outside group). This is a measured missed-content rate with gaze data, which corroborates the concern in the earlier batch that unguided viewers miss off-screen content, but the stimulus is an educational animation, the arrows were combined with text annotations, and the test answers were stressed in the annotations shown to cued groups, so learning gains cannot be credited to guidance alone. It is not a narrative-film study.
• articleIn a narrative 360-degree video, do on-screen guidance cues (arrow, radar, automatic reframing) send viewers to the main scene and help them follow the story, according to an independent open-access head-tracking study?
  Ortega-Alvarez, Matheus-Chacin, Garcia-Crespo and Ruiz-Arroyo (Multimedia Tools and Applications, CC BY, published 8 June 2022; version of record read) tested three non-diegetic visual cues in a 4-minute staged 360 story with 52 adults (13 per group, between subjects, head orientation logged every 0.1 s, no eye tracking). All three cues moved the head toward the main scene more than no cue (Tukey p<0.001), but only the Radar (+1.85 of 8 points, p=0.027) and the Auto Focus reframing (+2.31, p=0.004) improved a story-comprehension score; the Arrow did not (p=0.623). Auto Focus was the least accepted cue. This corroborates the earlier batch (C3-B204-UO-AS04) that forced rotation is disliked and that cue effects depend on cue design, and it adds a comprehension measure that candidates 03 and 04 of that batch lack. It cannot corroborate the diegetic-cue findings (sound, moving light) because only non-diegetic overlays were tested. Small groups, one staged scene, a phone-based HMD (VR BOX...
• articleIs there a peer-reviewed study of AI-generated 3D environments for previs with filmmaking professionals, and what does its abstract say was assessed?
  Leininger, Weber and Rothe (IMX 2025, pp. 60-78) report a pilot study with 15 filmmaking professionals comparing three AI-generated 3D environment types (Depth Mesh, 360 degree Panoramic Meshes, Gaussian Splatting) in an Unreal Engine 5 prototype called EnVisualAIzer. The abstract says splats suited high-fidelity previsualisation and panoramic meshes suited rapid ideation, and names limited interactivity and customisation. The abstract states no time saving. Only the abstract (via an index record) was read; the full text could not be read within the rules.
• articleWhich dated, attributable shoots or prototypes used an AI-generated 3D world or scene, and for each one what number does the source actually state and who stated it?
  Seven jobs were read first-hand (pages fetched as raw bytes). Six state a quantity, but every quantity is a company or named-person statement with no described measurement method: over ten environments in one afternoon (Moonshine/VIVE), hundreds of worlds over a few weeks and weeks-to-days (Pixomondo/World Labs launch video), months to about an hour (Veles/Volinga), 15 set-ups over five days (Quite Brilliant, image-based backgrounds, not 3D worlds), ten environments (Promise, Final Twist; no time figure), under an hour for a prototype (one VIVERSE developer). Gaussian Mansion states no number. No source gives a baseline that was actually run, a version, or a quality rating.
• articleHow long can an Odyssey interactive session run, and what concurrency, idle, queue and quota limits does the documentation state?
  The docs state per-stream 150 s and per-connection 60 min defaults, a 15-minute idle timeout, plan-dependent concurrent streams (Free example: 5), a 10-job simulation queue returning 429 when full, and non-refreshable 10-minute browser tokens. A restart after the 150 s lease costs a documented 1-2 s visual gap unless two clients roll over. Marketing wording ("can run for minutes", "120+ seconds of generation") is looser than these figures. All limits are for Odyssey-2 Pro; no limit for Odyssey-3 or Max was found.

More