Pith. sign in

REVIEW 32 cited by

MeshLRM: Large Reconstruction Model for High-Quality Meshes

Not yet reviewed by Pith; the record is open.

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 2404.12385 v2 pith:5OTBQLLG submitted 2024-04-18 cs.CV cs.GR

classification cs.CVcs.GR
keywords meshmeshlrmreconstructionallowsapproachhigh-qualityimageslarge
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose MeshLRM, a novel LRM-based approach that can reconstruct a high-quality mesh from merely four input images in less than one second. Different from previous large reconstruction models (LRMs) that focus on NeRF-based reconstruction, MeshLRM incorporates differentiable mesh extraction and rendering within the LRM framework. This allows for end-to-end mesh reconstruction by fine-tuning a pre-trained NeRF LRM with mesh rendering. Moreover, we improve the LRM architecture by simplifying several complex designs in previous LRMs. MeshLRM's NeRF initialization is sequentially trained with low- and high-resolution images; this new LRM training strategy enables significantly faster convergence and thereby leads to better quality with less compute. Our approach achieves state-of-the-art mesh reconstruction from sparse-view inputs and also allows for many downstream applications, including text-to-3D and single-image-to-3D generation. Project page: https://sarahweiii.github.io/meshlrm/

Discussion (0). Sign in to comment.

Forward citations

Cited by 32 Pith papers

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

  1. Stream3D: Sequential Multi-View 3D Generation via Evidential Memory

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    Stream3D is a training-free method that maintains temporal consistency in 3D generation from monocular streams by dynamically caching a fixed number of informative historical frames using an evidence score.

  2. R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    R-DMesh generates high-fidelity 4D meshes aligned to video by disentangling base mesh, motion, and a learned rectification jump offset inside a VAE, then using Triflow Attention and rectified-flow diffusion.

  3. Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    Free-Range Gaussians uses flow matching over Gaussian parameters to predict non-grid-aligned 3D Gaussians from multi-view images, enabling synthesis of plausible content in unobserved regions with fewer primitives tha...

  4. THOM: Generating Physically Plausible Hand-Object Meshes From Text

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    THOM is a training-free two-stage framework that generates physically plausible hand-object 3D meshes directly from text by combining text-guided Gaussians with contact-aware physics optimization and VLM refinement.

  5. Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters

    cs.CV 2025-12 unverdicted novelty 7.0 of 10

    A latent-space transformer framework poses 3D characters without skinning or fixed topologies, outperforming baselines and generalizing zero-shot to quadrupeds.

  6. ART: Articulated Reconstruction Transformer

    cs.CV 2025-12 unverdicted novelty 7.0 of 10

    ART is a category-agnostic transformer that maps sparse multi-state RGB images to per-part 3D geometry, texture, and articulation parameters via learnable part slots.

  7. Extracting Neural Materials from Multi-view Images

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    NeuMatEx extracts spatially varying neural materials from multi-view images by using a learned LMRM prior for initialization followed by uncertainty-guided inverse path tracing optimization.

  8. Extracting Neural Materials from Multi-view Images

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    NeuMatEx combines a Large Material Reconstruction Model for initialization and uncertainty-guided inverse path tracing to extract spatially varying neural materials from multi-view images.

  9. Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry Learning

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    Artic-O introduces an end-to-end feed-forward model that reconstructs articulated objects from sparse multi-state images via latent geometry learning and an image-grounded part-reasoning module, outperforming staged m...

  10. TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    TriSplat predicts oriented triangle primitives from images in one forward pass to produce simulation-ready 3D meshes with competitive rendering quality.

  11. Stream3D: Sequential Multi-View 3D Generation via Evidential Memory

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    Stream3D is a training-free method that maintains a fixed-size evidential memory of past frames to convert frozen view-conditioned 3D generators into consistent streaming generators.

  12. ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    ROAR-3D adds a token-wise view router and dual-stream attention to pretrained single-view 3D generators so they can use arbitrary unposed images for higher-fidelity output.

  13. R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    R-DMesh proposes a VAE-based disentanglement of base mesh, motion trajectories, and rectification offset plus Triflow Attention and rectified-flow diffusion to produce 4D meshes aligned to video despite initial pose mismatch.

  14. MeshReGen: A Unified 3D Geometry Regeneration Framework

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    MeshReGen introduces a conditioned 3D geometry regenerator with VecSet that learns a regeneration prior via self-supervision and reports state-of-the-art results on controllable generation tasks.

  15. MeshReGen: A Unified 3D Geometry Regeneration Framework

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    3D-ReGen is a conditioned 3D regenerator using VecSet that learns a regeneration prior from unlabeled 3D datasets via self-supervised tasks and achieves state-of-the-art results on controllable 3D geometry tasks.

  16. Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temp...

  17. LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

    cs.CV 2026-04 conditional novelty 6.0 of 10

    Scaling transformer context with sparse attention and 3D-aware block routing improves feed-forward 3D reconstruction and inverse rendering, closing much of the quality gap with dense-view optimization.

  18. LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

    cs.CV 2026-04 conditional novelty 6.0 of 10

    LSRM scales transformer context windows with native sparse attention and geometric routing to deliver high-fidelity feed-forward 3D reconstruction and inverse rendering that approaches dense optimization quality.

  19. LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

    cs.CV 2026-04 conditional novelty 6.0 of 10

    Scaling sparse transformer context to 20× more object tokens yields feed-forward 3D reconstructions with >2.4 dB higher PSNR and LPIPS that matches dense-view optimization.

  20. Multi-view Pyramid Transformer: Look Coarser to See Broader

    cs.CV 2025-12 conditional novelty 6.0 of 10

    MVP uses a two-level hierarchy of attention windows and token resolutions to reconstruct large 3D scenes from up to 256 input views in a single feed-forward pass, beating Long-LRM and iLRM on DL3DV and several zero-sh...

  21. Flux4D: Flow-based Unsupervised 4D Reconstruction

    cs.CV 2025-12 unverdicted novelty 6.0 of 10

    Flux4D reconstructs large-scale dynamic 4D scenes unsupervised by predicting moving 3D Gaussians from photometric losses and static regularization when trained across multiple scenes.

  22. 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.

  23. 4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A two-stage cascaded video diffusion model generates 16-view consistent videos from a monocular video, enabling higher-quality 4D content reconstruction.

  24. SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SurfaceSplat combines SDF-based coarse meshes with Gaussian splatting to improve sparse-view reconstruction and rendering, but the ablations do not isolate the effect of each component.

  25. AutoPartGen: Autogressive 3D Part Generation and Discovery

    cs.CV 2025-07 conditional novelty 6.0 of 10

    AutoPartGen generates 3D objects as a sequence of latent-space parts, conditioning each new part on previously generated parts, and reports state-of-the-art part completion on PartObjaverse-Tiny.

  26. TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

    cs.CV 2025-02 unverdicted novelty 6.0 of 10

    TripoSG generates high-fidelity 3D meshes from input images via a large-scale rectified flow transformer and hybrid-trained 3D VAE on a custom 2-million-sample dataset, claiming state-of-the-art fidelity and generalization.

  27. DVSM: Decoder-only View Synthesis Model Done Right

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    Decoder-only view synthesis model using KV-cache representation and weight sharing between reconstruction and rendering networks achieves new SOTA on novel view synthesis benchmarks.

  28. R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    R-DMesh uses a VAE with a learned rectification jump offset and Triflow Attention inside a rectified-flow diffusion transformer to produce video-aligned 4D meshes despite initial pose misalignment.

  29. ObjFiller3D: Scaling 3D Object Inpainting to Dense Multi-View Consistency

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    ObjFiller3D jointly optimizes a dense 360-degree ring of views to inpaint 3D objects with cross-view-consistent textures, reporting higher PSNR and LPIPS than per-view baselines at much lower runtime.

  30. Collaborative Multi-Modal Coding for High-Quality 3D Generation

    cs.CV 2025-08 conditional novelty 5.0 of 10

    TriMM fuses RGB, RGB-D, and point-cloud encoding into a shared triplane latent space and generates 3D assets from a single image with a latent diffusion model.

  31. KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos

    cs.CV 2024-11 unverdicted novelty 5.0 of 10

    KFC-W is a self-supervised 3D-aware video model trained on videos and multiview internet photos that produces geometrically consistent interpolations between unposed input images without any 3D annotations.

  32. AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation

    cs.CV 2026-04 unverdicted novelty 4.0 of 10

    AnimateAnyMesh++ animates arbitrary 3D meshes from text using an expanded 300K-identity DyMesh-XL dataset, a power-law topology-aware DyMeshVAE-Flex, and a variable-length rectified-flow generator to produce semantica...

Pith tools