If I run MEt3R, which reconstruction backbone do the paper and the repository say it uses, and which one do I get by default?
The paper text (arXiv v1 and v2) names DUSt3R as MEt3R's reconstruction model and says MASt3R was not used. The released code at commit ee0e175 defaults to a 'mast3r' backbone (MASt3R weights) and offers 'dust3r' and 'raft' as options, and the README overview still says DUSt3R. So a default run is not the configuration the paper text describes; to match the paper wording pass backbone="dust3r". Whether the paper's tables were produced with DUSt3R weights is not stated by any source read (see candidate 02).
The paper text (arXiv v1 and v2) names DUSt3R as MEt3R's reconstruction model and says MASt3R was not used. The released code at commit ee0e175 defaults to a 'mast3r' backbone (MASt3R weights) and offers 'dust3r' and 'raft' as options, and the README overview still says DUSt3R. So a default run is not the configuration the paper text describes; to match the paper wording pass backbone="dust3r". Whether the paper's tables were produced with DUSt3R weights is not stated by any source read (see candidate 02).
Curator qualifications: Conflict confirmed: the paper and README describe DUSt3R, while the released code defaults to MASt3R weights and vendors DUSt3R only inside the mast3r submodule. Wording precision: the paper says it does not use MASt3R's correspondences, which implies but does not literally state that MASt3R was not used. Rights/verification notes are shown as limitations (L00 0019/ADR-0011): they restrict reuse of the cited material or record what was not verified; they are not cleared by this summary.
Limitations: [component_reuse_restriction] Curator readbacks at MEt3R ee0e1752 (met3r.py, README (bytes equal pin), .gitmodules, LICENSE) and arXiv 2501.06336v2 HTML (bytes equal pin); commit 0369fa2 metadata via GitHub API GET; no code 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/html/2501.06336v2",
"note": "met3r/met3r.py at ee0e1752 L70-81; .gitmodules; README.md L28, L76, L129-130; arXiv v2 HTML (section 3.1 and method overview); LICENSE"
},
{
"url": "https://github.com/mohammadasim98/MEt3R/commits/master",
"note": "met3r/met3r.py at ee0e1752 L70-81; .gitmodules; README.md L28, L76, L129-130; arXiv v2 HTML (section 3.1 and method overview); LICENSE"
},
{
"url": "https://github.com/mohammadasim98/MEt3R/tree/ee0e1752898559e1a3e85e2e151d3edeb9b55f73",
"note": "met3r/met3r.py at ee0e1752 L70-81; .gitmodules; README.md L28, L76, L129-130; arXiv v2 HTML (section 3.1 and method overview); LICENSE"
}
]
}Evidence claims
- [sourced_fact] The paper text (arXiv v1 and v2) names DUSt3R as MEt3R's reconstruction model and says MASt3R was not used. The released code at commit ee0e175 defaults to a 'mast3r' backbone (MASt3R weights) and offers 'dust3r' and 'raft' as options, and the README overview still says DUSt3R. So a default run is not the configuration the paper text describes; to match the paper wording pass backbone="dust3r". Whether the paper's tables were produced with DUSt3R weights is not stated by any source read (see candidate 02). · locator: met3r/met3r.py at ee0e1752 L70-81; .gitmodules; README.md L28, L76, L129-130; arXiv v2 HTML (section 3.1 and method overview); LICENSE 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. |