AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

PS-NeRF: Neural Inverse Rendering for Multi-View Photometric Stereo

Wenqi Yang, Guanying Chen, Chaofeng Chen, Zhenfang Chen, Kwan-Yee K. Wong

ECCV 2022 · 3D vision › NeRF and radiance fields · approach: Few-shot neural rendering architectures · 83 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 multi-light normal regularization (ablation)NeRF · DiLiGenT-MV READINGNormal MAE: 55.55 -> 14.01Improved
add multi-light normal regularization (ablation)UNISURF · DiLiGenT-MV READINGNormal MAE: 19.68 -> 9.58Improved
add visibility modeling (ablation)PS-NeRF Stage II · Synth-PS BUNNYPSNR: 21.29 -> 25.88Improved
optimize light directions instead of fixing them (ablation)PS-NeRF Stage II · Synth-PS BUNNYPSNR: 24.04 -> 25.88Improved
add joint optimization (Stage II) (ablation)PS-NeRF · DiLiGenT-MV READINGNormal MAE: 9.58 -> 8.87Improved
refine lights by joint optimizationPS-NeRF · DiLiGenT-MV averageLight direction MAE: 6.89 -> 2.95Improved
use specular SG basis instead of Microfacet roughness (ablation)PS-NeRF · DiLiGenT-MV + BUNNY averageNormal MAE: 6.49 -> 6.24Improved
increase training views from 5 to 30UNISURF · Synth-Env BUNNYNormal MAE: 20.31 -> 9.11Improved
increase training views from 5 to 15PS-NeRF · Synth-Env BUNNYNormal MAE: 6.96 -> 5.17Improved
increase lights from 2 to 8PS-NeRF · DiLiGenT-MV READING (5 views)Normal MAE: 24.48 -> 11.52Improved
increase lights from 4 to 96PS-NeRF · DiLiGenT-MVNormal MAE: 6.75 vs. 5.18No clear effect
increase views from 10 to 15 (8 lights)PS-NeRF · DiLiGenT-MV READINGNormal MAE: 9.63 -> 9.99No clear effect

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