AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting

Ruofan Liang, Huiting Chen, Chunlin Li, Fan Chen, Selvakumar Panneer, Nandita Vijaykumar

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 65 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 indirect illumination modeling via reflected-ray marching (ablation)ENVIDR · Shiny Blender toasterPSNR: 25.46 -> 26.63Improved
add indirect illumination modeling via reflected-ray marching (ablation)ENVIDR · Shiny Blender toasternormal MAE (degrees): 7.64 -> 6.45Improved
add indirect illumination modeling via reflected-ray marching (ablation)ENVIDR · Shiny Blender coffeePSNR: 33.86 -> 34.45Improved
add indirect illumination modeling (ablation)ENVIDR · Blender materialsPSNR: 29.40 -> 29.51Improved
use l2 feature normalization instead of no normalization or instance normalization (ablation)ENVIDR neural renderer · Relighting (qualitative)relit specular highlight qualityImproved
use pre-trained, frozen diffuse/specular MLPs trained on PBR-rendered spheres (ablation)ENVIDR · Relighting (qualitative)reflection accuracyImproved
add SDF regularizations (Cauchy loss and back-face suppression) in early training (ablation)ENVIDR geometry · Surface normals (qualitative)surface qualityImproved
use ENVIDR instead of Ref-NeRF for surface geometryShiny Blender · Shiny Blender helmetnormal MAE (degrees): 29.48 -> 1.66Improved
ENVIDR vs Ref-NeRF on PSNR across scenesENVIDR · Shiny Blender plus Blender and real scenesPSNR: helmet 36.98 vs 29.68; ball 41.03 vs 47.46Mixed
ENVIDR vs NVDiffRecMC for relightingENVIDR · Relighting car/ficus/materialsPSNR: car 22.45 vs 24.71; ficus 24.64 vs 23.16Mixed

Later papers that compared with this method

6 later accepted papers report ENVIDR as a baseline in their results tables; 3 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