AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

NeILF: Neural Incident Light Field for Physically-Based Material Estimation

Yao Yao, Jingyang Zhang, Jingbo Liu, Yihang Qu, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan

ECCV 2022 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 115 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 fixed Fibonacci sampling instead of random uniform sampling for incident directions (ablation)NeILF · Synthetic scenes (average)rendering PSNR: 29.73 -> 32.09Improved
use fixed Fibonacci sampling instead of random uniform sampling for incident directions (ablation)NeILF · Synthetic scenes (average)base color PSNR: 12.45 -> 16.30Improved
increase ray samples from 32 to 128 (ablation)NeILF · Synthetic scenes (average)rendering PSNR: 30.57 -> 32.09Improved
increase ray samples from 32 to 128 (ablation)NeILF · Synthetic scenes (average)roughness PSNR: 19.49 -> 16.49Hurt
increase ray samples from 32 to 128 (ablation)NeILF · Synthetic scenes (average)base color PSNR: 13.40 -> 16.30Improved
add position input to the light field (NeILF instead of direction-only Ne-ENV) (ablation)NeILF · DTU scan-75rendering PSNR: 19.52 -> 23.46Improved
use NeILF instead of SG environment map under mixed lightingNeILF · Synthetic Combined-objects Mix-studiobase color PSNR: 13.16 -> 16.88Improved
use NeILF instead of SG environment map under single object environment lightingNeILF · Synthetic Single-helmet Env-citybase color PSNR: 20.61 -> 16.36Hurt
use NeILF instead of SG environment map for novel view renderingNeILF · Synthetic Single-helmet Env-cityrendering PSNR: 29.73 -> 31.57Improved
add bilateral smoothness regularization on roughness and metallic (ablation)NeILF · real-world DTU and BlendedMVSvisual BRDF qualityImproved
add bilateral smoothness and Lambertian regularizations (ablation)NeILF · Synthetic scenesPSNRNo clear effect

Later papers that compared with this method

7 later accepted papers report NeILF++ as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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