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

• URL: http://arxiv.org/abs/2605.26230v1
• Date: Mon, 25 May 2026 18:01:05 GMT
• Title: Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
• Abstract summary: 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.<n>This design exploits the geometry-aware feature representations of the 3D reconstructor to effectively recover accurate scene geometry.<n>By employing an additional RGB image decoder, the refined representations can also be used to restore high-quality RGB images.
• Score: 36.377286063905395
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction [69.35136600319714]
  We introduce a new approach to high-fidelity 3D scene reconstruction from multi-view RGB images.<n>We cast scene reconstruction as conditional 3D generation over a set of spatially-localized, overlapping chunks.<n>We obtain high-fidelity results that outperform cutting-edge reconstruction methods by 16%.
  arXiv  Detail & Related papers  (2026-05-22T17:49:59Z)
• RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction [51.07270086169647]
  RealX3D groups corruptions into four families, including illumination, scattering, and blurring, and captures each at multiple severity levels.<n>Each scene includes high-resolution capture, RAW images, and dense laser scans, from which we derive world-scale meshes and metric depth.
  arXiv  Detail & Related papers  (2025-12-29T12:57:19Z)
• AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance [36.125573065910594]
  Active 3D reconstruction enables an agent to autonomously select viewpoints to obtain accurate and complete scene geometry.<n>We propose AREA3D, an active reconstruction agent that leverages feed-forward 3D reconstruction models and vision-language guidance.<n>Our framework decouples view-uncertainty modeling from the underlying feed-forward reconstructor, enabling precise uncertainty estimation without expensive online optimization.
  arXiv  Detail & Related papers  (2025-11-28T06:17:02Z)
• Surf3R: Rapid Surface Reconstruction from Sparse RGB Views in Seconds [34.38496869014632]
  Surf3R is an end-to-end feedforward approach that reconstructs 3D surfaces from sparse views without estimating camera poses.<n>Our method employs a multi-branch and multi-view decoding architecture in which multiple reference views jointly guide the reconstruction process.
  arXiv  Detail & Related papers  (2025-08-06T14:53:42Z)
• RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions [67.48495052903534]
  We propose a general and efficient multi-view feature enhancement module, RobustGS.<n>It substantially improves the robustness of feedforward 3DGS methods under various adverse imaging conditions.<n>The RobustGS module can be seamlessly integrated into existing pretrained pipelines in a plug-and-play manner.
  arXiv  Detail & Related papers  (2025-08-05T04:50:29Z)
• An Evaluation of DUSt3R/MASt3R/VGGT 3D Reconstruction on Photogrammetric Aerial Blocks [17.58704237530163]
  3D computer vision algorithms continue to advance in handling sparse, unordered image sets.<n>Recently developed foundational models for 3D reconstruction have attracted attention due to their ability to handle very sparse image overlaps.<n>This paper conducts a comprehensive evaluation of the pre-trained DUSt3R/MASt3R/VGGT models on the aerial blocks of the UseGeo dataset for pose estimation and dense 3D reconstruction.
  arXiv  Detail & Related papers  (2025-07-20T03:09:04Z)
• Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction [11.220655907305515]
  We introduce a monocular-guided refinement module that integrates monocular geometric priors into multi-view reconstruction frameworks.<n>Our method achieves substantial improvements in both mutli-view camera pose estimation and point cloud accuracy.
  arXiv  Detail & Related papers  (2025-04-18T02:33:12Z)
• Regist3R: Incremental Registration with Stereo Foundation Model [22.636140424781455]
  Multi-view 3D reconstruction has remained an essential yet challenging problem in the field of computer vision.<n>We propose Regist3R, a novel stereo foundation model tailored for efficient and scalable incremental reconstruction.<n>We evaluate Regist3R on public datasets for camera pose estimation and 3D reconstruction.
  arXiv  Detail & Related papers  (2025-04-16T02:46:53Z)
• PE3R: Perception-Efficient 3D Reconstruction [54.730257992806116]
  Perception-Efficient 3D Reconstruction (PE3R) is a novel framework designed to enhance both accuracy and efficiency.<n>The framework achieves a minimum 9-fold speedup in 3D semantic field reconstruction, along with substantial gains in perception accuracy and reconstruction precision.
  arXiv  Detail & Related papers  (2025-03-10T16:29:10Z)
• GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
  We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-21T17:49:31Z)
• GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting [81.03553265684184]
  We introduce GeoGS3D, a framework for reconstructing detailed 3D objects from single-view images. We propose a novel metric, Gaussian Divergence Significance (GDS), to prune unnecessary operations during optimization. Experiments demonstrate that GeoGS3D generates images with high consistency across views and reconstructs high-quality 3D objects.
  arXiv  Detail & Related papers  (2024-03-15T12:24:36Z)
• UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections [87.191742674543]
  We propose UniSDF, a general purpose 3D reconstruction method that can reconstruct large complex scenes with reflections.<n>Our method is able to robustly reconstruct complex large-scale scenes with fine details and reflective surfaces, leading to the best overall performance.
  arXiv  Detail & Related papers  (2023-12-20T18:59:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.