AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Dynamic Scene Understanding Through Object-Centric Voxelization and Neural Rendering

Yanpeng Zhao, Yiwei Hao, Siyu Gao, Yunbo Wang, Xiaokang Yang

TPAMI 2025 · 3D vision › NeRF and radiance fields · approach: NeRF for scene decomposition and understanding · 7 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 object-centric voxelization (ablation)DynaVol-S · 3ObjRandPSNR: 32.15 -> 32.58Improved
add object-centric voxelization (ablation)DynaVol-S · 8ObjFallPSNR: 30.76 -> 31.78Improved
add forward deformation network (ablation)DynaVol-S · 8ObjFallmIOU: 75.91 -> 85.41Improved
add CRF post-processing (ablation)DynaVol-S · 3ObjRandPSNR: 32.57 -> 32.58No clear effect
add multi-grids joint optimization stage (ablation)DynaVol-S · 3ObjRandPSNR: 30.48 -> 32.58Improved
add warmup stage before joint optimization (vs joint optimization from scratch) (ablation)DynaVol-S · 3ObjRandmIOU: 14.73 -> 90.60Improved
increase latent codes from N=5 to N=10 (ablation)DynaVol-S · 8ObjFallmIOU: 42.80 -> 85.41Improved
increase latent codes from N=10 to N=15 (ablation)DynaVol-S · 8ObjFallmIOU: 85.41 -> 85.46No clear effect
vary density threshold delta_den from 1 to 2 (ablation)DynaVol-S · 8ObjFallmIOU: 85.41 -> 88.41Mixed
add per-point RGB loss (alpha_p=0.01 vs 0) (ablation)DynaVol-S · 3ObjRandPSNR: 30.00 -> 32.58Improved
raise per-point RGB loss weight from 0.01 to 0.1 (ablation)DynaVol-S · 3ObjRandmIOU: 90.60 -> 31.61Hurt
add semantic features (DynaVol to DynaVol-S)DynaVol-S · Real-world scene decomposition (average)mIOU: 41.71 -> 88.95Improved

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