AI Paper Atlas

Research map / 3D vision / Depth and stereo

L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing

Ziyu Chen, Chenjing Ding, Jianfei Guo, Dongliang Wang, Yikang Li, Xuan Xiao, Wei Wu, Li Song

ECCV 2022 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 8 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 L-Tracing instead of volumetric integrationlight visibility estimation · 1024 points x 512 lightstime (s): 13.36 -> 1.07Improved
use L-Tracing instead of volumetric integrationlight visibility estimation · 4096 points x 512 lightstime (s): 64.75 -> 4.13Improved
use L-Tracing (binary visibility) instead of volume integration (ablation)reflectance factorization · NeRFactor synthetic, albedoPSNR: 27.594 -> 27.296Hurt
use L-Tracing (binary visibility) instead of volume integration (ablation)reflectance factorization · NeRFactor synthetic, view interpolationPSNR: 32.229 -> 31.194Hurt
use L-Tracing (binary visibility) instead of volume integration (ablation)reflectance factorization · NeRFactor synthetic, HDR relightingSSIM: 0.917 -> 0.920Improved
use L-Tracing instead of volume integration (ablation)light visibility quality · drums OLAT2shadow sharpness (qualitative)Improved
increase tracing iterations from 20 to 80 (ablation)L-Tracing framework · NeRFactor synthetic, view interpolationPSNR: 31.194 -> 31.889No clear effect
increase tracing iterations from 20 to 80 (ablation)L-Tracing framework · NeRFactor synthetic, view interpolationLPIPS: 0.063 -> 0.060No clear effect
use L-Tracing light visibility instead of precomputed volume-integration caches in NeRFactorNeRFactor framework · NeRFactor synthetic, view interpolationPSNR: 30.288 -> 31.194Improved

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