AI Paper Atlas

Research map / 3D vision / Face and shape

MS3D: High-Quality 3D Generation via Multi-Scale Representation Modeling

Guan Luo, Jianfeng Zhang

ICCV 2025 · 3D vision › Face and shape · approach: Textured mesh generation · 1 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 multi-scale SAMv2 features instead of Dinov2 (ablation)MS3D · GSO ablation (GT images input)PSNR: 32.10 -> 34.08Improved
add multi-scale SAMv2 features instead of Dinov2 (ablation)MS3D · GSO ablation (GT images input)LPIPS-N: 0.050 -> 0.036Improved
add multi-scale features instead of single-scale SAMv2 (ablation)MS3D · GSO ablation (GT images input)PSNR: 30.16 -> 34.08Improved
add multi-scale features instead of single-scale SAMv2 (ablation)MS3D · GSO ablation (GT images input)Chamfer distance: 0.010 -> 0.010No clear effect
raise max voxel resolution from 64 to 256 (ablation)MS3D · GSO ablation (GT images input)PSNR-N: 30.56 -> 34.71Improved
raise max voxel resolution from 128 to 256 (ablation)MS3D · GSO ablation (GT images input)PSNR-N: 33.25 -> 34.71Improved
raise max voxel resolution from 64 to 256 (ablation)MS3D · GSO ablation (GT images input)F-Score: 0.981 -> 0.992Improved
add multi-scale rendering supervision (ablation)MS3D · GSO ablation (GT images input)PSNR: 32.32 -> 34.08Improved
add multi-scale rendering supervision (24h training comparison) (ablation)MS3D · GSO ablation (GT images input)PSNR: 32.32 -> 33.52Improved
replace MeshFormer with MS3DMeshFormer · GSO single image to 3DChamfer distance: 0.031 -> 0.026Improved
replace TRELLIS with MS3DTRELLIS · OmniObject3D single image to 3DF-Score: 0.933 -> 0.963Improved
replace MeshFormer with MS3DMeshFormer · OmniObject3D single image to 3DPSNR: 18.85 -> 21.86Improved

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