What does an open paper co-authored by a studio rig team say about the inverse rig problem (solving blendshape weights from mocap) and its failure modes?
Rackovic et al. (3Lateral/Epic byline) define a good inverse-rig solution by data fidelity, stability under later hand edits, low weight cardinality, frame-to-frame continuity and respect for weight limits; they add quadratic corrective terms for realistic rigs, report SQP fits accurate meshes but with non-sparse, non-smooth weights, and claim up to 45% lower RMS mesh error with their MM algorithm on their own benchmarks.
Rackovic et al. (3Lateral/Epic byline) define a good inverse-rig solution by data fidelity, stability under later hand edits, low weight cardinality, frame-to-frame continuity and respect for weight limits; they add quadratic corrective terms for realistic rigs, report SQP fits accurate meshes but with non-sparse, non-smooth weights, and claim up to 45% lower RMS mesh error with their MM algorithm on their own benchmarks.
Curator qualifications: Pages and paper read 2026-10-22; no capture or solve run. Chaudhuri et al. (S22) claim not re-read by curator. Author-run benchmarks only; no independent replication.
Limitations: Pages and paper read 2026-10-22; no capture or solve run.
Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.
Structured fields
{
"citations": [
{
"url": "https://arxiv.org/abs/2302.04843v2",
"note": "arXiv abs 2302.04843v2 (live), abstract and licence link; arXiv 2302.04843v2 PDF, byline and Section 1"
},
{
"url": "https://arxiv.org/pdf/2007.06759v2",
"note": "arXiv abs 2302.04843v2 (live), abstract and licence link; arXiv 2302.04843v2 PDF, byline and Section 1"
},
{
"url": "https://arxiv.org/pdf/2302.04843v2",
"note": "observed URL (dated/alias form of the cited catalogue source; canonical identity retained)"
}
]
}Evidence claims
- [sourced_fact] Rackovic et al. (3Lateral/Epic byline) define a good inverse-rig solution by data fidelity, stability under later hand edits, low weight cardinality, frame-to-frame continuity and respect for weight limits; they add quadratic corrective terms for realistic rigs, report SQP fits accurate meshes but with non-sparse, non-smooth weights, and claim up to 45% lower RMS mesh error with their MM algorithm on their own benchmarks. · locator: arXiv abs 2302.04843v2 (live), abstract and licence link; arXiv 2302.04843v2 PDF, byline and Section 1 source
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Applies to this original summary only, not to the cited sources. |