Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth

• URL: http://arxiv.org/abs/2607.15600v1
• Date: Fri, 17 Jul 2026 03:49:14 GMT
• Title: Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth
• Abstract summary: We propose a novel framework that transfers the scale-aware geometric priors of multi-view models into monocular depth foundation models.<n>Specifically, we introduce an Epipolar Distillation (EpiDistill), which enables the single-view prediction model to retain epipolar attention patterns and maintain geometric consistency without requiring multi-view inputs at inference.
• Score: 11.871264497562008
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Monocular depth foundation models have demonstrated remarkable generalization capabilities across diverse environments. However, they continue to struggle with metric depth estimation in diverse environments. This limitation stems from the inherent scale ambiguity of single-view inference, leading to misaligned scale predictions even when the relative geometry is accurate. Conversely, recent multi-view foundation models leverage cross-view cues to learn robust scene-level geometry and consistent scale. Yet, these benefits typically vanish during single-image inference, as the absence of explicit geometric constraints causes performance to degrade. To bridge this gap, we propose a novel framework that transfers the scale-aware geometric priors of multi-view models into monocular depth foundation models. Specifically, we introduce an Epipolar Distillation (EpiDistill), an approach utilizing Rectified Stereo Tokens, which enables the single-view prediction model to retain epipolar attention patterns and maintain geometric consistency without requiring multi-view inputs at inference. Experimental results demonstrate that our method significantly improves zero-shot metric depth estimation, particularly on challenging datasets like ETH3D and DIODE where scale alignment is critical. Furthermore, our approach is model-agnostic, consistently boosting the performance of state-of-the-art ViT-based models, including UniDepthV2 and DepthPro.

Related papers

• Panoramic Scene Analysis: A Survey from Distortion-Aware Engineering to Sphere-Native Foundation Modeling [1.8625021794520016]
  Panoramic images capture the complete visual sphere in a single frame, providing spatial context unattainable by conventional cameras.<n>Yet this completeness comes at a geometric cost: the 2-sphere cannot be faithfully mapped to the plane, and every planar representation introduces distortions that violate the assumptions underlying standard vision architectures.<n>This survey traces the evolution of panoramic scene analysis along a methodological trajectory, from projection-based adaptation, through distortion-aware engineering, to sphere-native modeling and geometry-aware tokenization for foundation models.
  arXiv  Detail & Related papers  (2026-06-26T05:54:38Z)
• Pose Anything Anywhere:Model-free Object Poses from Arbitrary References [64.58017857473774]
  We present PANY, a model-free framework that seamlessly supports both RGB and RGB-D inputs.<n>It operates on one or sparse pose-free reference views, and generalizes effectively to novel objects.<n>It achieves state-of-the-art performance across multiple benchmarks, substantially outperforming existing model-free methods.
  arXiv  Detail & Related papers  (2026-06-22T17:23:57Z)
• FoundationSLAM: Unleashing the Power of Depth Foundation Models for End-to-End Dense Visual SLAM [50.9765003472032]
  FoundationSLAM is a learning-based monocular dense SLAM system for accurate and robust tracking and mapping.<n>Our core idea is to bridge flow estimation with reasoning by leveraging the guidance from foundation depth models.
  arXiv  Detail & Related papers  (2025-12-31T17:57:45Z)
• VGD: Visual Geometry Gaussian Splatting for Feed-Forward Surround-view Driving Reconstruction [26.668204454537246]
  We introduce textbfVisual Gaussian Driving (VGD), a novel feed-forward end-to-end learning framework designed to address this challenge.<n>We show that our approach significantly outperforms state-of-the-art methods in both objective metrics and subjective quality under various settings.
  arXiv  Detail & Related papers  (2025-10-22T13:28:49Z)
• Dens3R: A Foundation Model for 3D Geometry Prediction [44.13431776180547]
  Dens3R is a 3D foundation model designed for joint geometric dense prediction.<n>By integrating image-pair matching features with intrinsic invariance modeling, Dens3R accurately regresses multiple geometric quantities.
  arXiv  Detail & Related papers  (2025-07-22T07:22:30Z)
• Relative Pose Estimation through Affine Corrections of Monocular Depth Priors [69.59216331861437]
  We develop three solvers for relative pose estimation that explicitly account for independent affine (scale and shift) ambiguities.<n>We propose a hybrid estimation pipeline that combines our proposed solvers with classic point-based solvers and epipolar constraints.
  arXiv  Detail & Related papers  (2025-01-09T18:58:30Z)
• GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image [94.56927147492738]
  We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes from single images. We show that leveraging diffusion priors can markedly improve generalization, detail preservation, and efficiency in resource usage. We propose a simple yet effective strategy to segregate the complex data distribution of various scenes into distinct sub-distributions.
  arXiv  Detail & Related papers  (2024-03-18T17:50:41Z)
• A Model for Multi-View Residual Covariances based on Perspective Deformation [88.21738020902411]
  We derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups. We validate our model with synthetic and real data and integrate it into photometric and feature-based Bundle Adjustment.
  arXiv  Detail & Related papers  (2022-02-01T21:21:56Z)
• Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency [114.02182755620784]
  We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our framework is shown to outperform the state-of-the-art depth and motion estimation methods.
  arXiv  Detail & Related papers  (2021-02-04T14:26:42Z)

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.