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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Jin Hyeon, Lee, Jaeeun, Kim, Claire, Oh, Kyoungjin, Cho, Paul Hyunbin, Min, Jaewon, Choi, Yeji, Park, Jihye, Park, Hyunhee, Park, Minkyu, Kim, Seungryong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917533084286976
author Kim, Jin Hyeon
Lee, Jaeeun
Kim, Claire
Oh, Kyoungjin
Cho, Paul Hyunbin
Min, Jaewon
Choi, Yeji
Park, Jihye
Park, Hyunhee
Park, Minkyu
Kim, Seungryong
author_facet Kim, Jin Hyeon
Lee, Jaeeun
Kim, Claire
Oh, Kyoungjin
Cho, Paul Hyunbin
Min, Jaewon
Choi, Yeji
Park, Jihye
Park, Hyunhee
Park, Minkyu
Kim, Seungryong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_26230
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
Kim, Jin Hyeon
Lee, Jaeeun
Kim, Claire
Oh, Kyoungjin
Cho, Paul Hyunbin
Min, Jaewon
Choi, Yeji
Park, Jihye
Park, Hyunhee
Park, Minkyu
Kim, Seungryong
Computer Vision and Pattern Recognition
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.
title Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.26230