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

Mengchen Zhang; Yang Li; Chunshi Wang; Tong Wu; Chunchao Guo

cs.CVOct 13, 2026

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

Authors: Mengchen Zhang, Yang Li, Chunshi Wang, Tong Wu, Chunchao Guo

Organizations: Zhejiang University · Tencent Hunyuan · Fudan University

Abstract

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/.

Figures & tables

Figure 2: WorldRecon Pipeline. Left: Given unposed multi-view RGB images, VGGT- $\Omega$ reconstructs a global point cloud. The point cloud is divided into overlapping blocks, each paired with local RGBA images and predicted camera poses. Middle: For each block, DINOv3 image tokens and Plücker-ray camera tokens are fused into fixed-length multi-view tokens, while a point-cloud encoder extracts geometric tokens. Right: Three cascaded flow models progressively generate the sparse structure, detailed geometry, and PBR materials.

Method	3D Geometry			Coverage	Depth				Normal
Method	CD $\downarrow$	F-score $\uparrow$	NC $\uparrow$	Complete. $\uparrow$	RMSE $\downarrow$	AbsRel $\downarrow$	LPIPS $\downarrow$	CLIP $\uparrow$	Angular $\downarrow$	LPIPS $\downarrow$	CLIP $\uparrow$
VGGT- $\Omega$ +TSDF	0.2934	0.4596	0.5433	0.7363	0.5906	0.1548	0.4873	0.8679	20.9899	0.6188	0.8568
Murre	0.5295	0.2426	0.4729	0.4572	0.8847	0.2397	0.5273	0.8332	22.6896	0.6671	0.8542
MonoSDF	0.2558	0.4936	0.5730	0.9056	0.6052	0.1616	0.2566	0.9161	18.2223	0.3560	0.9062
FineRecon	0.2448	0.5301	0.6252	0.8126	0.5578	0.1490	0.3398	0.8906	17.6099	0.4419	0.8845
GenRecon	0.1861	0.6196	0.6128	0.9587	0.5348	0.1666	0.2548	0.9490	17.9822	0.3139	0.9543

Table 1: Comparisons on Synthetic Scenes. We evaluate 3D geometry and 2D depth and normal metrics on

30

scenes from 3D-FRONT, which is synthetic and large-scale.

Method	3D Geometry			Coverage	Depth				Normal
Method	CD $\downarrow$	F-score $\uparrow$	NC $\uparrow$	Complete. $\uparrow$	RMSE $\downarrow$	AbsRel $\downarrow$	LPIPS $\downarrow$	CLIP $\uparrow$	Angular $\downarrow$	LPIPS $\downarrow$	CLIP $\uparrow$
VGGT- $\Omega$ +TSDF	0.1121	0.7467	0.7036	0.8737	0.3984	0.1433	0.3907	0.8991	25.4852	0.5075	0.8888
Murre	0.1756	0.5640	0.6222	0.5567	0.6619	0.1863	0.5587	0.8690	28.4193	0.5642	0.8761
MonoSDF	0.1665	0.6224	0.6913	0.9670	0.6293	0.3043	0.2705	0.9273	23.7527	0.3861	0.9016
FineRecon	0.1259	0.6861	0.7226	0.9388	0.4405	0.1673	0.2707	0.9183	22.6830	0.4043	0.8886
GenRecon	0.1227	0.5901	0.5969	0.9722	0.6837	0.3048	0.3862	0.9291	31.5722	0.4711	0.9172

Table 2: Comparisons on Real-world Scenes. We evaluate 3D geometry and 2D depth and normal metrics on

30

scenes from Scannet++. Best results are bold , and second-best results are underlined .

Figure 3: Qualitative Comparison. Mesh reconstruction results on evaluation scenes, including both synthetic and real-world examples. We show close-up views of interior details (top) and complete scene reconstructions (bottom). Compared with the baselines, WorldRecon produces more complete and geometrically consistent reconstructions with substantially fewer artifacts.

Components				3D Metrics			2D Metrics
SS	Geo&Mat	Inpaint	Stitch	CD $\downarrow$	F-score $\uparrow$	NC $\uparrow$	Complete. $\uparrow$	MAE $\downarrow$	AbsRel $\downarrow$	Angular $\downarrow$	RGB CLIP $\uparrow$
$\times$	$\times$	$\times$	$\times$	0.4003	0.2013	0.1682	0.7377	1.1847	0.6160	48.6471	0.7255
✓	$\times$	$\times$	$\times$	0.0996	0.7438	0.7173	0.9722	0.1659	0.0980	19.6434	0.8244
✓	✓	$\times$	$\times$	0.0954	0.7624	0.7349	0.9858	0.1589	0.0890	17.7610	0.8609
✓	✓	✓	$\times$	0.1023	0.7482	0.7202	0.9868	0.1439	0.0830	17.2462	0.8609
✓	✓	✓	✓	0.0830	0.8226	0.7640	0.9894	0.1394	0.0815	16.5789	0.8671

Table 3: Ablation Study. We conduct quantitative ablation studies of the key components of WorldRecon on 30 scenes from 3D-FRONT and ScanNet++.

Figure 4: Qualitative Ablation Study. We qualitatively compare the same ablation settings as in Table 3 on a 3D-FRONT scene unseen during training. We show the complete scene reconstruction for each variant and the ground truth, while colored circles highlight corresponding local details.

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Stage	Image	Latent	Points	GPUs	Global Batch	LR	EMA	Adaptation
SS generation	$512$	$16^{3}$	$8192$	$32$	$128$	$1{\times}10^{-4}$	$0.9999$	full
SS inpainting	$512$	$16^{3}$	$8192$	$32$	$128$	$3{\times}10^{-5}$	$0.9999$	full
Geometry generation	$512$	$32^{3}$	–	$16$	$64$	$1{\times}10^{-4}$	$0.9995$	full
Geometry inpainting	$512$	$32^{3}$	–	$16$	$64$	$3{\times}10^{-5}$	$0.9995$	full
Material generation	$512$	$32^{3}$	–	$16$	$96$	$3{\times}10^{-5}$	$0.9995$	LoRA
Material inpainting	$512$	$32^{3}$	–	$16$	$96$	$1{\times}10^{-5}$	$0.9995$	LoRA

Appendix

Table S1: Training configurations . We report the image and latent resolutions, point-cloud size, number of GPUs, global batch size, learning rate, EMA decay, and adaptation strategy for each generation and inpainting stage.

Figure S1: Large-Scale Scene Generation. Reconstruction results for large-scale, multi-room scenes, with top-down views (left) and detailed interior views (right).

Figure S2: Comparison with Agentic Baseline. Given the same 32 views, we show GT, ours, and a GPT-6 Astra agent adapted from BVB Tang et al. (2026) (left to right). Our method yields more faithful reconstructions, while the agent simplifies or omits objects and distorts the scene layout.

Figure S3: Failure case. Inaccurate reconstruction from VGGT- $\Omega$ lead to missing geometry in unobserved regions. Nevertheless, WorldRecon remains robust to substantial pose errors and still faithfully reconstructs the areas that are covered by the input views.

3D Reconstruction

3D reconstruction recovers a scene’s shape, appearance, and camera motion from images, video, depth, or other sensor measurements.

See all 930 papers

GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
May 22, 2026Katharina Schmid, Nicolas von Lützow, Jozef Hladký +23D Reconstruction Multi-View 3D Reconstruction
Technical University of Munich · Computing Systems Lab, Huawei Technologies, Switzerland
PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction
Mar 6, 2026Xiang Zhang, Sohyun Yoo, Hongrui Wu +3Autoregressive 3D Scene Generation 3D Mesh Reconstruction
UC San Diego · Lambda, Inc.
T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images
Oct 2, 2026Atsuhiro Noguchi, Tianhan Xu, Yiming Liang +5Large-Scale 3D Reconstruction 3D Reconstruction
Preferred Networks, Inc. · The University of Tokyo

May 22, 2026J/K move · Enter open · S save

GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction

Katharina Schmid, Nicolas von Lützow, Jozef Hladký, Angela Dai+1

Technical University of Munich · Computing Systems Lab, Huawei Technologies, Switzerland

3D Reconstruction Multi-View 3D Reconstruction 3D Mesh Reconstruction Indoor Scene Reconstruction Conditional Generative Modeling

Open paper AskPDF arXiv

We introduce a new approach to high-fidelity 3D scene reconstruction from multi-view RGB images that tightly couples reconstruction with a strong generative 3D prior. We cast scene reconstruction as conditional 3D generation over a set of spatially-localized, overlapping chunks that together tile the scene, scaling generation to large scene extents. Crucially, we inherit the fidelity and completeness of state-of-the-art generative shape models -- we use Trellis.2 as an example -- which we generalize to the scene level. To this end, we propose a projection-based conditioning mechanism that lifts posed multi-view image features into a coherent 3D representation aligned with the generative model, independent of view ordering and spatially anchored to the scene, yielding high-fidelity, multi-view consistent generated geometry. This enables lifting the strong object-level prior of Trellis.2 to multi-view, scene-scale generation, producing faithful, editable PBR mesh reconstructions of indoor environments. As a result, we obtain high-fidelity results that outperform cutting-edge reconstruction methods by 16%.

Abstract

3D Reconstruction

Explore similar work

GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction

PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction

T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images