Pith. sign in

REVIEW 5 cited by

MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.10198 v1 pith:JAJZHMQK submitted 2024-08-19 cs.CV cs.GR

Minghua Liu , Chong Zeng , Xinyue Wei , Ruoxi Shi , Linghao Chen , Chao Xu , Mengqi Zhang , Zhaoning Wang
show 4 more authors
Xiaoshuai Zhang Isabella Liu Hongzhi Wu Hao Su
This is my paper
classification cs.CVcs.GR
keywords high-qualityinputmeshesmeshformermodelsreconstructiontrainingbias
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Open-world 3D reconstruction models have recently garnered significant attention. However, without sufficient 3D inductive bias, existing methods typically entail expensive training costs and struggle to extract high-quality 3D meshes. In this work, we introduce MeshFormer, a sparse-view reconstruction model that explicitly leverages 3D native structure, input guidance, and training supervision. Specifically, instead of using a triplane representation, we store features in 3D sparse voxels and combine transformers with 3D convolutions to leverage an explicit 3D structure and projective bias. In addition to sparse-view RGB input, we require the network to take input and generate corresponding normal maps. The input normal maps can be predicted by 2D diffusion models, significantly aiding in the guidance and refinement of the geometry's learning. Moreover, by combining Signed Distance Function (SDF) supervision with surface rendering, we directly learn to generate high-quality meshes without the need for complex multi-stage training processes. By incorporating these explicit 3D biases, MeshFormer can be trained efficiently and deliver high-quality textured meshes with fine-grained geometric details. It can also be integrated with 2D diffusion models to enable fast single-image-to-3D and text-to-3D tasks. Project page: https://meshformer3d.github.io

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. AIMold: An Autonomous AI-based Pipeline for Complex Mold Design

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A new dataset and deep learning pipeline generate upper and lower molds, parting surfaces, and auxiliary components for complex injection-molded parts.

  2. Intrinsic and Triangulation-Agnostic Attention: A Simple and Powerful Approach for Learning on Meshes

    cs.GR 2026-07 conditional novelty 6.0 of 10

    Mass-weighted FEM attention on intrinsic mesh features is triangulation-agnostic and beats current mesh and point-cloud baselines on several geometry-learning benchmarks.

  3. CharacterShot: Controllable and Consistent 4D Character Animation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A new pipeline generates pose-controlled, view-consistent 4D character animations from one reference image and a 2D pose sequence, backed by a new 13,115-character dataset and benchmark.

  4. Isotropic Remeshing with Inter-Angle Optimization

    cs.CG 2025-07 conditional novelty 5.0 of 10

    This paper introduces an isotropic remeshing method that gates split, collapse, and flip edits with inter-angle and dihedral checks, and uses MLS upsampling to preserve surface geometry.

  5. 3D Arena: An Open Platform for Generative 3D Evaluation

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A crowdsourced voting platform with 123,000 votes reveals that people judge AI-generated 3D assets mainly by visual appearance rather than technical quality.

Pith tools