AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

DynPoint: Dynamic Neural Point For View Synthesis

Kaichen Zhou, Jia-Xing Zhong, Sangyun Shin, Kai Lu, Yiyuan Yang, Andrew Markham, Niki Trigoni

NeurIPS 2023 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 3 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
use multiple-step (2K adjacent frame) aggregation (ablation)DynPoint · Nvidia dynamic scenesPSNR (avg): 14.78 -> 26.53Improved
use multiple-step (2K adjacent frame) aggregation (ablation)DynPoint · Nvidia dynamic scenesLPIPS (avg): 0.666 -> 0.068Improved
increase neighbouring frames from K=3 to K=6 (ablation)DynPoint · Nvidia dynamic scenesPSNR (avg): 18.94 -> 26.53Improved
increase neighbouring frames from K=3 to K=6 (ablation)DynPoint · Nvidia dynamic scenesLPIPS (avg): 0.357 -> 0.068Improved
add hierarchical neural point cloud (ablation)DynPoint · Nvidia dynamic scenesPSNR (avg): 24.38 -> 26.53Improved
add hierarchical neural point cloud (ablation)DynPoint · Nvidia dynamic scenesLPIPS (avg): 0.161 -> 0.068Improved
DynPoint versus RoDYN on LPIPSDynPoint · Nvidia dynamic scenesLPIPS (avg): 0.065 -> 0.068Hurt
DynPoint versus DynamicNeRF on PSNRDynPoint · Nvidia dynamic scenesPSNR (avg): 26.10 -> 26.53Improved
DynPoint versus NSFFDynPoint · Nerfies datasetPSNR (avg): 25.93 -> 26.41Improved
DynPoint versus NSFFDynPoint · HyperNeRF datasetPSNR (avg): 26.40 -> 27.50Improved
DynPoint versus Nerfies on LPIPSDynPoint · Nerfies datasetLPIPS (avg): 0.233 -> 0.241Hurt
DynPoint versus NSFF on iPhoneDynPoint · iPhone datasetmPSNR (avg): 15.46 -> 16.89Improved

Later papers that compared with this method

2 later accepted papers report DynPoint as a baseline in their results tables; 1 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