Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction

Hugging Face Daily Papers Papers

Summary

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.

Multi-view 3D reconstruction has achieved remarkable progress with the advent of feed-forward 3D reconstruction models. However, these models are typically trained and evaluated under ideal, degradation-free imaging conditions, whereas real-world observations often contain degradations that differ significantly from such settings. Improving robustness for multi-view 3D reconstruction under degraded conditions therefore remains an important challenge. We present Geometry-Aware Representation Denoising (GARD), a novel framework that performs diffusion-based multi-view restoration directly in the feature space of a feed-forward 3D reconstruction model. This design exploits the geometry-aware feature representations of the 3D reconstructor to effectively recover accurate scene geometry. Furthermore, by employing an additional RGB image decoder, the refined representations can also be used to restore high-quality RGB images, thereby enabling the simultaneous recovery of 3D scene geometry and high-quality imagery. Comprehensive experiments on the Depth Anything 3 (DA3) benchmark demonstrate the effectiveness of the proposed GARD framework.
Original Article
View Cached Full Text

Cached at: 05/27/26, 02:47 AM

Paper page - Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction

Source: https://huggingface.co/papers/2605.26230

Abstract

A novel diffusion-based framework for multi-view 3D reconstruction that restores both scene geometry and high-quality imagery from degraded inputs by operating in the feature space of a 3D reconstructor.

Multi-view 3D reconstructionhas achieved remarkable progress with the advent of feed-forward 3D reconstruction models. However, these models are typically trained and evaluated under ideal, degradation-free imaging conditions, whereas real-world observations often contain degradations that differ significantly from such settings. Improving robustness formulti-view 3D reconstructionunder degraded conditions therefore remains an important challenge. We present Geometry-Aware Representation Denoising (GARD), a novel framework that performs diffusion-based multi-view restoration directly in thefeature spaceof a feed-forward 3D reconstruction model. This design exploits the geometry-aware feature representations of the 3D reconstructor to effectively recover accurate scene geometry. Furthermore, by employing an additionalRGB image decoder, the refined representations can also be used to restore high-quality RGB images, thereby enabling the simultaneous recovery of 3D scene geometry and high-quality imagery. Comprehensive experiments on the Depth Anything 3 (DA3) benchmark demonstrate the effectiveness of the proposed GARD framework.

View arXiv pageView PDFProject pageGitHub10Add to collection

Get this paper in your agent:

hf papers read 2605\.26230

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/2605.26230 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.26230 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.26230 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

Geometry-Aware Tabular Diffusion

arXiv cs.LG

Introduces Geometry-Aware Tabular Diffusion (GATD), which augments tabular diffusion denoisers with explicit pairwise geometric features. Achieves state-of-the-art performance on ten benchmarks while using significantly fewer parameters.

Unified Panoramic Geometry Estimation via Multi-View Foundation Models

Hugging Face Daily Papers

PaGeR adapts the multi-view perspective foundation model Depth Anything 3 to predict scale-invariant and metric depth, surface normals, and sky segmentation from a single equirectangular image, using a fixed cubemap representation that keeps VRAM and runtime constant. The paper also releases the ZüriPano and PanoInfinigen datasets.