AI Paper Atlas

Research map / 3D vision / Face and shape

CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model

Zhengyi Wang, Yikai Wang, Yifei Chen, Chendong Xiang, Shuo Chen, Dajiang Yu, Chongxuan Li, Hang Su, Jun Zhu

ECCV 2024 · 3D vision › Face and shape · approach: Textured mesh generation · 193 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 random resizing to multi-view diffusion training (ablation)ImageDream 6-view + Zero-SNR · GSO subset novel view synthesisPSNR: 29.13 -> 29.36Improved
add Zero-SNR training to multi-view diffusion (ablation)ImageDream 6-view · GSO subset novel view synthesisPSNR: 28.99 -> 29.13Improved
add contour augmentation to multi-view diffusion training (ablation)ImageDream 6-view + Zero-SNR + resizing · GSO subset novel view synthesisPSNR: 29.36 -> 28.92Hurt
add canonical coordinate map (CCM) input to the reconstruction U-Net (ablation)CRM reconstruction model · qualitative geometrygeometry quality (qualitative)Improved
use convolutional U-Net with six orthographic inputs instead of transformer (LRM) for triplaneCRM · GSO geometryChamfer Distance: 0.0168 -> 0.0094Improved
use convolutional U-Net with spatial prior instead of transformerCRM · reconstruction training costtraining costImproved
CRM versus Wonder3D on F-scoreCRM · GSO geometryF-score (%): 76.75 -> 79.38Improved

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