AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos

Jinxi Li, Ziyang Song, Bo Yang

NeurIPS 2023 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 5 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
Jointly optimize keyframe radiance and interframe velocity fields (ablation)NVFi · Dynamic Object Dataset extrapolationPSNR: 24.792 -> 27.594Improved
Add divergence-free and momentum physics constraints (ablation)NVFi · Dynamic Object Dataset extrapolationPSNR: 25.537 -> 27.594Improved
Use 8 keyframes rather than 16 (ablation)NVFi · Dynamic Object Dataset extrapolationPSNR: 27.594 -> 27.490No clear effect
Increase keyframes from 16 to 32 (ablation)NVFi · Dynamic Object Dataset extrapolationPSNR: 27.594 -> 24.902Hurt
Increase keyframes from 4 to 8 (ablation)NVFi · Dynamic Indoor Scene Dataset extrapolationPSNR: 29.745 -> 29.093Hurt
Increase keyframes from 4 to 16 (ablation)NVFi · Dynamic Indoor Scene Dataset extrapolationPSNR: 29.745 -> 26.235Hurt
Reduce training cameras from 12 to 6 (ablation)NVFi · Dynamic Object Dataset extrapolationPSNR: 27.594 -> 25.114Hurt
Reduce training cameras from 12 to 3 (ablation)NVFi · Dynamic Object Dataset extrapolationPSNR: 27.594 -> 21.370Hurt
Learn velocity with NVFi rather than D-NeRF deformationMotion transfer to Gnome-new · Gnome-new motion transferPSNR: 16.124 -> 16.178No clear effect

Later papers that compared with this method

3 later accepted papers report NVFi as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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