WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World

Hugging Face Daily Papers Papers
3d-reconstruction generative-models multi-view mesh-reconstruction scene-generation computer-vision

Summary

WorldRecon 提出一种生成式多视角网格重建框架，可从无位姿 RGB 图像重建大规模 3D 场景的完整网格。它将 TRELLIS.2 生成模型与重建式条件架构结合，通过邻域感知潜在修补和因果世界生成保证场景级一致性，在合成与真实室内场景上分别将 Chamfer 距离降低 14.9% 和 43.1%，达到最先进性能。

Reconstructing complete, high-quality meshes of large-scale scenes from unposed multi-view images requires faithful geometric grounding while plausibly completing surfaces that are unobserved or only sparsely captured. We present WorldRecon, a generative multi-view reconstruction framework for recovering complete, large-scale 3D scene meshes from unposed RGB images. WorldRecon uses a coarse, noisy global point cloud and camera poses estimated from the input images by a reconstruction model as a global scaffold for whole-scene generation and partitions it into overlapping spatial blocks. To robustly leverage these imperfect geometric priors, we equip the native 3D generative model TRELLIS.2 with a dedicated reconstruction-based conditioning architecture that generates each block from its local point-cloud crop and block-relevant image observations, producing sparse structure, detailed geometry, and PBR materials. To maintain scene-level coherence, we introduce neighbour-aware latent inpainting and a causal world-generation procedure that propagates structural, geometric, and material context across overlapping blocks. Together, these designs scale multi-view generative reconstruction to large-scale scenes, yielding coherent, unified meshes. Extensive experiments demonstrate that WorldRecon achieves state-of-the-art reconstruction performance, reducing Chamfer distance by 14.9% and 43.1% while improving F-score by 17.3% and 12.0% over the strongest baselines on synthetic and real-world indoor scenes, respectively, thereby demonstrating faithful and complete generative reconstruction as well as strong sim-to-real generalization. Project page: https://kszpxxzmc.github.io/WorldRecon-website/.
Original Article
View Cached Full Text

Cached at: 10/14/26, 10:54 AM

Paper page - WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World

Source: https://huggingface.co/papers/2610.18846

Abstract

Reconstructingcomplete,high-qualitymeshesoflarge-scalescenesfromunposedmulti-viewimagesrequiresfaithfulgeometricgroundingwhileplausiblycompletingsurfacesthatareunobservedoronlysparselycaptured.WepresentWorldRecon,agenerativemulti-viewreconstructionframeworkforrecoveringcomplete,large-scale3DscenemeshesfromunposedRGBimages.WorldReconusesacoarse,noisyglobalpointcloudandcameraposesestimatedfromtheinputimagesbyareconstructionmodelasaglobalscaffoldforwhole-scenegenerationandpartitionsitintooverlappingspatialblocks.Torobustlyleveragetheseimperfectgeometricpriors,weequipthenative3DgenerativemodelTRELLIS.2withadedicatedreconstruction-basedconditioningarchitecturethatgenerateseachblockfromitslocalpoint-cloudcropandblock-relevantimageobservations,producingsparsestructure,detailedgeometry,andPBRmaterials.Tomaintainscene-levelcoherence,weintroduceneighbour-awarelatentinpaintingandacausalworld-generationprocedurethatpropagatesstructural,geometric,andmaterialcontextacrossoverlappingblocks.Together,thesedesignsscalemulti-viewgenerativereconstructiontolarge-scalescenes,yieldingcoherent,unifiedmeshes.ExtensiveexperimentsdemonstratethatWorldReconachievesstate-of-the-artreconstructionperformance,reducingChamferdistanceby14.9%and43.1%whileimprovingF-scoreby17.3%and12.0%overthestrongestbaselinesonsyntheticandreal-worldindoorscenes,respectively,therebydemonstratingfaithfulandcompletegenerativereconstructionaswellasstrongsim-to-realgeneralization.Projectpage:https://kszpxxzmc.github.io/WorldRecon-website/.

View arXiv pageView PDFProject pageGitHub3Add to collection

Get this paper in your agent:

hf papers read 2610\.18846

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.18846 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.18846 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.18846 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

Hugging Face Daily Papers

PixWorld presents a unified pixel-space diffusion approach for 3D scene reconstruction and generation, overcoming limitations of latent-space methods by using direct image-level supervision and geometry-aware feature alignment. The method outperforms prior generation methods and matches state-of-the-art reconstruction methods.