AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Velox: Learning Representations of 4D Geometry and Appearance

Anagh Malik, Dorian Chan, Xiaoming Zhao, David B. Lindell, Oncel Tuzel, Jen-Hao Rick Chang

CVPR 2026 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 0 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
add texture augmentation (ablation)Velox-S · Objaverse reconstruction (256 held-out scenes), small modelPSNR: 32.41 -> 33.93Improved
add texture augmentation (ablation)Velox-S · Objaverse reconstruction (256 held-out scenes), small modelChamfer (x1e5): 43.34 -> 38.79Improved
add texture augmentation (ablation)Velox-S · Objaverse reconstruction (256 held-out scenes), small modelFVD: 99.16 -> 66.78Improved
encode jointly over time instead of per-frame LiToVelox · Objaverse reconstruction (256 held-out scenes)PSNR: 32.55 -> 35.11Improved
use trained voxel decoder instead of sampled points for Gaussian decoder voxels (ablation)Velox · Objaverse reconstruction (256 held-out scenes)PSNR: 34.25 -> 35.11Improved
use decoded voxels instead of GT voxels (ablation)Velox · Objaverse reconstruction (256 held-out scenes)PSNR: 35.39 -> 35.11No clear effect
model time-conditioned geometry and appearance instead of deformations (GVF)Velox · Objaverse reconstruction (256 held-out scenes)PSNR: 26.45 -> 35.11Improved
use Heun 100 steps instead of Euler 10 steps at sampling (ablation)Velox video-to-4D · Video-to-4D, Objaverse, conditioning viewPSNR: 22.19 -> 24.04Improved
use Velox tokens for video-to-4D instead of L4GMVelox · Video-to-4D, Objaverse, novel viewPSNR: 18.30 -> 20.62Improved
use Velox tokens for tracking instead of CoTracker3 w/ GT depthVelox · Objaverse 3D trackingAPD 3D (all points): 0.755 -> 0.835Improved
use Velox tokens for tracking instead of SpatialTrackerV2Velox · Objaverse 3D trackingOcclusion accuracy: 0.897 -> 0.871Hurt

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