AI Paper Atlas

Research map / 3D vision / 3D generation

MatMart: Material Reconstruction of 3D Objects via Diffusion

Xiuchao Wu, Pengfei Zhu, Jiangjing Lyu, Xinguo Liu, Jie Guo, Yanwen Guo, Weiwei Xu, Chengfei Lyu

CVPR 2026 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 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 view-material cross-attention (VMCA) to progressive inference (ablation)MatMart · Objaverse 3-view, 1024x1024Rendering FID: 28.58 -> 26.20Improved
add material priors (baked UV materials projected to view) to generation (ablation)MatMart · Objaverse 3-view, 1024x1024Rendering FID: 34.93 -> 26.20Improved
add stage-1 prediction and texture baking before generation (ablation)MatMart · Objaverse 3-view, 1024x1024Rendering FID: 42.40 -> 26.20Improved
increase inference resolution from 512 to 1024 (ablation)MatMart · Objaverse 3-viewRendering FID: 31.34 -> 26.20Improved
increase inference resolution from 512 to 1024 (ablation)MatMart · Objaverse single-viewRendering FID: 31.64 -> 31.49No clear effect
increase number of input views (ablation)MatMart · Objaverse, 1024x1024FID: 37.39 -> 29.05 -> 27.95 -> 27.71 (1, 5, 10, 20 views)Improved
increase number of input views (ablation)MatMart · Objaverse, 1024x1024peak GPU memory (GB): 24.03 for all view countsNo clear effect
use stage-1 prediction + UV-space TexGEN generation instead of view-space generationMatMart · Objaverse single-viewRendering FID: 31.64 -> 54.10 (vs MatMart 512)Hurt
replace Material Anything's RGB-then-predict pipeline with predict-then-generate materialsMatMart · Objaverse single-viewRendering FID: 54.16 -> 31.64Improved
change generation group size (ablation)MatMart · Objaversereconstruction qualityNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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