AI Paper Atlas

Research map / Image generation / Super-resolution

Super-Resolution 3D Human Shape from a Single Low-Resolution Image

Marco Pesavento, Marco Volino, Adrian Hilton

ECCV 2022 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 17 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
train all modules end to end (ablation)SuRS · THuman2.0 (LR input 256)Chamfer distance (cm): 1.375 -> 0.931Improved
train all modules end to end instead of feature extractor then MLPs (ablation)SuRS · THuman2.0 (LR input 256)Chamfer distance (cm): 1.261 -> 0.931Improved
train all modules end to end instead of extractor+MR-MLP then SR-MLP (ablation)SuRS · THuman2.0 (LR input 256)Chamfer distance (cm): 1.035 -> 0.931Improved
add U-Net high-resolution feature extractor with 2D reconstruction loss (ablation)SuRS · THuman2.0 (LR input 256)Chamfer distance (cm): 1.090 -> 0.931Improved
add SR-MLP stage on top of MR-MLP (ablation)SuRS · THuman2.0 (LR input 256)Chamfer distance (cm): 1.044 -> 0.931Improved
add MR-MLP conditioning to SR-MLP (ablation)SuRS · THuman2.0 (LR input 256)Chamfer distance (cm): 1.039 -> 0.931Improved
add difference loss Ldiff (ablation)SuRS · THuman2.0 (LR input 256)Chamfer distance (cm): 1.020 -> 0.931Improved
add difference loss Ldiff (ablation)SuRS · 3D PeopleChamfer distance (cm): 1.127 -> 1.057Improved
decimate LR ground-truth shape to 1000 faces instead of 100000 (ablation)SuRS · THuman2.0 (LR input 256)Chamfer distance (cm): 0.942 -> 0.931Improved
decimate LR ground-truth shape to 1000 faces instead of 100000 (ablation)SuRS · 3D PeopleChamfer distance (cm): 1.147 -> 1.057Improved
decimate LR ground-truth shape to 1000 faces (ablation)SuRS · THuman2.0 (LR input 256)P2S (cm): 1.116 -> 1.151No clear effect
use SuRS instead of PIFuHD with normal mapsSuRS · THuman2.0 (LR input 256)P2S (cm): 1.046 -> 1.151Hurt

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