AI Paper Atlas

Research map / 3D vision / Face and shape

Neural Reconstruction of Relightable Human Model from Monocular Video

Wenzhang Sun, Yunlong Che, Han Huang, Yandong Guo

ICCV 2023 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 16 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 MLP normal with inverse-gradient weak supervision instead of raw inverse gradient (ablation)relightable human model · Synthetic dynamic humanPSNR: 26.76 -> 29.87Improved
add normal prior (weak supervision) to MLP normal prediction (ablation)relightable human model · Synthetic dynamic humanPSNR: 27.63 -> 29.87Improved
add sparsity prior on base color (ablation)relightable human model · Synthetic dynamic humanPSNR: 29.41 -> 29.87Improved
add sparsity prior on base color (ablation)relightable human model · Synthetic dynamic human (normal map)MSE: 0.0598 -> 0.0617Hurt
add inverse mapping fine-tuning (ablation)relightable human model · Synthetic dynamic humanPSNR: 28.40 -> 29.87Improved
add progressive training (ablation)relightable human model · Synthetic dynamic humanPSNR: 27.61 -> 29.87Improved
use inverse gradient normal versus MLP without prior (ablation)relightable human model · Synthetic dynamic humanPSNR: 27.63 -> 26.76Hurt
use proposed monocular relighting framework versus Relighting4Ddynamic human relighting · Synthetic dynamic humanPSNR: 27.57 -> 29.87Improved

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