AI Paper Atlas

Research map / 3D vision / Face and shape

Relighting4D: Neural Relightable Human from Videos

Zhaoxi Chen, Ziwei Liu

ECCV 2022 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 59 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 latent feature psi_t(x) to geometry/reflectance MLPs (ablation)Relighting4D · BlenderHuman (16 scenes)PSNR (relighting): 21.1163 -> 26.1475Improved
add smoothness regularization tau_V, tau_n (ablation)Relighting4D · BlenderHuman (16 scenes)PSNR (relighting): 25.3504 -> 26.1475Improved
add baked geometry supervision (ablation)Relighting4D · BlenderHuman (16 scenes)PSNR (relighting): 22.4221 -> 26.1475Improved
add baked geometry supervision (ablation)Relighting4D · BlenderHuman (16 scenes)Normal map error (degrees): 57.0452 -> 32.1803Improved
add global sparsity prior (minimize H_A) on diffuse map (ablation)Relighting4D · BlenderHuman (16 scenes)PSNR (relighting): 27.7545 -> 26.1475Mixed
add global sparsity prior (minimize H_A) on diffuse map (ablation)Relighting4D · BlenderHuman (16 scenes) diffuse mapPSNR: 24.0195 -> 28.9517Improved
add progressive spatial resolution training (ablation)Relighting4D · BlenderHuman (16 scenes)PSNR (relighting): 25.5562 -> 26.1475Improved
use progressive training instead of constant resolution (ablation)Relighting4D · People-SnapshotPSNR: 34.56 -> 36.65Improved
physically based rendering vs NB+LE learnable light embeddingRelighting4D · BlenderHuman (16 scenes)PSNR (relighting): 22.7957 -> 26.1475Improved
Relighting4D vs PhySGrelighting · BlenderHuman (16 scenes)PSNR (relighting): 23.8810 -> 26.1475Improved

Later papers that compared with this method

7 later accepted papers report Relighting4D as a baseline in their results tables; 7 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