AI Paper Atlas

Research map / Image generation / Image restoration

DynIBaR: Neural Dynamic Image-Based Rendering

Zhengqi Li, Qianqian Wang, Forrester Cole, Richard Tucker, Noah Snavely

CVPR 2023 · Image generation › Image restoration · approach: Image harmonization and color transformation · 172 citations (OpenAlex)

Read the paper

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
Use DynIBaR instead of the strongest baseline, NSFFDynamic scene view synthesis · Nvidia Dynamic Scene Dataset, FullLPIPS: 0.062 -> 0.027Improved
Use DynIBaR instead of the strongest baseline, NSFFDynamic scene view synthesis · Nvidia Dynamic Scene Dataset, Dynamic OnlyLPIPS: 0.144 -> 0.062Improved
Use DynIBaR instead of the strongest baseline, NSFFDynamic scene view synthesis · UCSD Dynamic Scenes Dataset, FullPSNR: 31.75 -> 36.47Improved
Use DynIBaR instead of the strongest baseline, NSFFDynamic scene view synthesis · UCSD Dynamic Scenes Dataset, FullLPIPS: 0.034 -> 0.014Improved
Use DynIBaR instead of the strongest baseline, DVSDynamic scene view synthesis · UCSD Dynamic Scenes Dataset, Dynamic OnlyPSNR: 26.57 -> 28.01Improved
Use DynIBaR instead of the strongest baseline, DVSDynamic scene view synthesis · UCSD Dynamic Scenes Dataset, Dynamic OnlyLPIPS: 0.096 -> 0.042Improved
Add cross-time temporal consistency (ablation)DynIBaR · Nvidia Dynamic Scene Dataset, FullPSNR: 27.57 -> 30.77Improved
Use motion trajectories rather than scene flow fields for feature aggregation (ablation)DynIBaR · Nvidia Dynamic Scene Dataset, FullPSNR: 29.42 -> 30.77Improved
Use motion trajectories rather than multiple scene-flow vectors to nearby times (ablation)DynIBaR · Nvidia Dynamic Scene Dataset, FullPSNR: 29.59 -> 30.77Improved
Add a time-invariant static scene model (ablation)DynIBaR · Nvidia Dynamic Scene Dataset, FullPSNR: 28.19 -> 30.77Improved
Add masked reconstruction supervision from motion segmentation masks (ablation)DynIBaR · Nvidia Dynamic Scene Dataset, FullPSNR: 29.95 -> 30.77Improved
Add regularization loss (ablation)DynIBaR · Nvidia Dynamic Scene Dataset, FullPSNR: 29.46 -> 30.77Improved

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