AI Paper Atlas

Research map / 3D vision / Face and shape

Analysis-by-Synthesis Transformer for Single-View 3D Reconstruction

Dian Jia, Xiaoqian Ruan, Kun Xia, Zhiming Zou, Le Wang, Wei Tang

ECCV 2024 · 3D vision › Face and shape · approach: Textured mesh generation · 4 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 Shape Transformer with learnable vertex queries (ablation)AST · CUB-200-2011Mask IoU (%): 74.6 -> 81.6Improved
add Texture Transformer with texture queries (ablation)AST · CUB-200-2011SSIM (%): 65.3 -> 86.0Improved
add Texture Transformer (ablation)AST · CUB-200-2011Mask IoU (%): 75.3 -> 81.6Improved
add Shape Transformer (ablation)AST · ShapeNet TableChamfer-L1: 0.314 -> 0.218Improved
add Texture Transformer (ablation)AST · ShapeNet TableChamfer-L1: 0.240 -> 0.218Improved
AST vs HybridInv test-time optimizationAST · CUB-200-2011Mask IoU (%): 84.4 -> 81.6Hurt
AST vs Unicorn on ShapeNet shape and textureAST · ShapeNetChamfer-L1: Lamp 0.523 -> 0.356; Speaker 0.235 -> 0.244; Bench 0.159 -> 0.164Mixed
AST vs Unicorn on OmniObject3D bananaAST · OmniObject3D BananaChamfer-L1: 0.375 -> 0.272Improved

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