AI Paper Atlas

Research map / 3D vision / 3D generation

Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis

Hongyuan Chen, Xingyu Chen, Zexiang Xu, Anpei Chen

CVPR 2026 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
reconstruct motion on a reference mesh instead of per-frame generation and alignment (V2M4)Motion 3-to-4 · Motion-80 shortChamfer Distance: 0.3437 -> 0.1113Improved
reconstruct motion on a reference mesh instead of feed-forward Gaussian prediction (L4GM)Motion 3-to-4 · Motion-80 shortChamfer Distance: 0.3561 -> 0.1113Improved
use ground-truth static mesh as referenceMotion 3-to-4 · Motion-80 shortChamfer Distance: 0.1113 -> 0.0437Improved
use ground-truth static mesh as referenceMotion 3-to-4 · Motion-80 shortFVD: 1175.89 -> 497.43Improved
frame-wise transformer on long sequencesMotion 3-to-4 · Motion-80 longF-Score: 0.1652 (V2M4) -> 0.2347Improved
compare with L4GM on appearanceMotion 3-to-4 · Motion-80 shortFVD: 1120.67 (L4GM) vs 1175.89Hurt
compare with L4GM on appearanceMotion 3-to-4 · Motion-80 shortLPIPS: 0.1487 (L4GM) vs 0.1495Mixed
compare with baselines on Consistent4DMotion 3-to-4 · Consistent4DCLIP: 0.8482 (V2M4) -> 0.8609Improved
compare with baselines on Consistent4DMotion 3-to-4 · Consistent4DFVD: 1207.79 (L4GM) vs 1260.06Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy