AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Modeling Indirect Illumination for Inverse Rendering

CVPR 2022 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 164 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 visibility and indirect illumination modeling instead of assuming shared environment lighting (ablation)Ours · Synthetic test images, four scenesrelighting PSNR: 25.3919 -> 25.5934Helped
Add visibility and indirect illumination modeling instead of assuming shared environment lighting (ablation)Ours · Synthetic test images, four scenesview synthesis PSNR: 26.4971 -> 26.1918Hurt
Add indirect illumination modeling (ablation)Ours · Synthetic test images, four scenesalbedo PSNR: 23.7422 -> 24.1608Helped
Add indirect illumination modeling (ablation)Ours · Synthetic test images, four scenesrelighting PSNR: 25.4957 -> 25.5934Helped
Add the sparse latent-space BRDF representation (ablation)Ours · Synthetic test images, four scenesroughness MSE: 0.0783 -> 0.0723Helped
Add the sparse latent-space BRDF representation (ablation)Ours · Synthetic test images, four scenesview synthesis PSNR: 26.1846 -> 26.1918No clear effect

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