GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
Summary
GenRecon introduces a method for 3D scene reconstruction that integrates generative 3D priors with multi-view image conditioning, achieving high-fidelity, editable mesh reconstructions of indoor environments and outperforming existing methods by 16%.
View Cached Full Text
Cached at: 05/25/26, 02:35 AM
Paper page - GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
Source: https://huggingface.co/papers/2605.23888
Abstract
A novel method for 3D scene reconstruction that integrates generative 3D priors with multi-view image conditioning to produce high-fidelity, editable mesh reconstructions of indoor environments.
We introduce a new approach to high-fidelity3D scene reconstructionfrom multi-view RGB images that tightly couples reconstruction with a stronggenerative 3D prior. We cast scene reconstruction asconditional 3D generationover 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 useTrellis.2as an example -- which we generalize to the scene level. To this end, we propose aprojection-based conditioning mechanismthat lifts posedmulti-view image featuresinto acoherent 3D representationaligned 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 ofTrellis.2to multi-view, scene-scale generation, producing faithful, editablePBR mesh reconstructionsof indoor environments. As a result, we obtain high-fidelity results that outperform cutting-edge reconstruction methods by 16%.
View arXiv pageView PDFProject pageAdd to collection
Get this paper in your agent:
hf papers read 2605\.23888
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/2605.23888 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.23888 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.23888 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
AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model
AnyRecon proposes a scalable framework for 3D reconstruction from arbitrary sparse inputs using a video diffusion model with persistent scene memory and geometry-aware conditioning.
4D Human-Scene Reconstruction from Low-Overlap Captures
Proposes StudioRecon, a method for 4D human-scene reconstruction from low-overlap camera captures, using separate priors for backgrounds (video diffusion) and humans (SMPL), with a recursive enhancement module. Accepted to SIGGRAPH 2026, outperforming prior methods by +1.5 to +5.0 dB PSNR.
Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
Introduces GARD, a diffusion-based framework that operates in the feature space of a feed-forward 3D reconstructor to jointly recover scene geometry and high-quality imagery from degraded inputs.
ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video
ReViV is a unified framework for holistic egocentric 4D reconstruction that simultaneously reconstructs viewer (body, hand, gaze) and view (depth, camera trajectory) dynamics from a single monocular RGB video using a Masked Generative Egocentric Transformer, achieving state-of-the-art accuracy and efficiency.
RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting
RelightFormer introduces a feed-forward generative Transformer for direct single- and multi-view image relighting, using cross-attention for illumination injection and permutation-invariant encodings for unordered views, trained on a massive synthetic dataset to achieve state-of-the-art visual quality.