AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fields

Sungheon Park, Minjung Son, Seokhwan Jang, Young Chun Ahn, Ji-Yeon Kim, Nahyup Kang

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 67 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 the smoothness regularizer to Ours-NN (ablation)Ours-NN · D-NeRFPSNR: 30.18 -> 32.73Improved
Add static features alongside dynamic features (ablation)Neural representation · D-NeRFPSNR: 30.91 -> 32.73Improved
Add static features alongside dynamic features (ablation)Grid representation · D-NeRFPSNR: 29.08 -> 29.84Improved
Use two interpolation levels with n0=5 and n1=20 instead of one level with n0=2 (ablation)Neural representation · D-NeRF 3dprinterPSNR: 20.64 -> 21.15Improved
Add a third interpolation level (ablation)Neural representation · D-NeRF 3dprinterPSNR: 21.73 -> 21.15; 21.73 -> 21.12Hurt
Interpolate feature vectors rather than time embeddings (ablation)Ours-NN · HyperNeRF interpPSNR: +0.5dBImproved
Use smaller feature dimensions (ablation)Grid representation · D-NeRFPSNRMixed

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