Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-05-25 with 39 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Jin Hyeon Kim et al. |
| Year | 2026 |
| HF Upvotes | 39 |
| arXiv | 2605.26230 |
| Download | |
| HF Page | View on Hugging Face |
Abstract
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.
Engineering Breakdown
The Problem
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.
The Approach
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.
Key Results
Comprehensive experiments on the Depth Anything 3 (DA3) benchmark demonstrate the effectiveness of the proposed GARD framework.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Geometryaware
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::