Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces

• URL: http://arxiv.org/abs/2503.22209v1
• Date: Fri, 28 Mar 2025 07:56:59 GMT
• Title: Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces
• Authors: Wonhyeok Choi, Kyumin Hwang, Minwoo Choi, Kiljoon Han, Wonjoon Choi, Mingyu Shin, Sunghoon Im,
• Abstract summary: Self-supervised monocular depth estimation (SSMDE) has gained attention in the field of deep learning.<n>We propose a novel framework that incorporates intrinsic image decomposition into SSMDE.<n>Our method synergistically trains for both monocular depth estimation and intrinsic image decomposition.
• Score: 10.557788087220509
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Self-supervised monocular depth estimation (SSMDE) has gained attention in the field of deep learning as it estimates depth without requiring ground truth depth maps. This approach typically uses a photometric consistency loss between a synthesized image, generated from the estimated depth, and the original image, thereby reducing the need for extensive dataset acquisition. However, the conventional photometric consistency loss relies on the Lambertian assumption, which often leads to significant errors when dealing with reflective surfaces that deviate from this model. To address this limitation, we propose a novel framework that incorporates intrinsic image decomposition into SSMDE. Our method synergistically trains for both monocular depth estimation and intrinsic image decomposition. The accurate depth estimation facilitates multi-image consistency for intrinsic image decomposition by aligning different view coordinate systems, while the decomposition process identifies reflective areas and excludes corrupted gradients from the depth training process. Furthermore, our framework introduces a pseudo-depth generation and knowledge distillation technique to further enhance the performance of the student model across both reflective and non-reflective surfaces. Comprehensive evaluations on multiple datasets show that our approach significantly outperforms existing SSMDE baselines in depth prediction, especially on reflective surfaces.

Related papers

• Occlusion-Aware Self-Supervised Monocular Depth Estimation for Weak-Texture Endoscopic Images [1.1084686909647639]
  We propose a self-supervised monocular depth estimation network tailored for endoscopic scenes. Existing methods, though accurate, typically assume consistent illumination. These variations lead to incorrect geometric interpretations and unreliable self-supervised signals.
  arXiv  Detail & Related papers  (2025-04-24T14:12:57Z)
• A Novel Solution for Drone Photogrammetry with Low-overlap Aerial Images using Monocular Depth Estimation [6.689484367905018]
  Low-overlap aerial imagery poses significant challenges to traditional photogrammetric methods.<n>We propose a novel workflow based on monocular depth estimation to address the limitations of conventional techniques.
  arXiv  Detail & Related papers  (2025-03-06T14:59:38Z)
• Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining [14.432210570631577]
  Self-supervised monocular depth estimation (SSMDE) aims to predict the dense depth map of a monocular image.<n>It struggles with reflective surfaces, as they violate the assumptions of Lambertian reflectance.<n>We propose a novel training strategy for an SSMDE by leveraging triplet mining to pinpoint reflective regions at the pixel level.
  arXiv  Detail & Related papers  (2025-02-20T13:59:40Z)
• Adaptive Stereo Depth Estimation with Multi-Spectral Images Across All Lighting Conditions [58.88917836512819]
  We propose a novel framework incorporating stereo depth estimation to enforce accurate geometric constraints. To mitigate the effects of poor lighting on stereo matching, we introduce Degradation Masking. Our method achieves state-of-the-art (SOTA) performance on the Multi-Spectral Stereo (MS2) dataset.
  arXiv  Detail & Related papers  (2024-11-06T03:30:46Z)
• NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images [62.752710734332894]
  NeRSP is a Neural 3D reconstruction technique for Reflective surfaces with Sparse Polarized images. We derive photometric and geometric cues from the polarimetric image formation model and multiview azimuth consistency. We achieve the state-of-the-art surface reconstruction results with only 6 views as input.
  arXiv  Detail & Related papers  (2024-06-11T09:53:18Z)
• Self-supervised Monocular Depth Estimation on Water Scenes via Specular Reflection Prior [3.2120448116996103]
  This paper proposes the first self-supervision for deep-learning depth estimation on water scenes via intra-frame priors. In the first stage, a water segmentation network is performed to separate the reflection components from the entire image. The photometric re-projection error, incorporating SmoothL1 and a novel photometric adaptive SSIM, is formulated to optimize pose and depth estimation.
  arXiv  Detail & Related papers  (2024-04-10T17:25:42Z)
• End-to-end Learning for Joint Depth and Image Reconstruction from Diffracted Rotation [10.896567381206715]
  We propose a novel end-to-end learning approach for depth from diffracted rotation. Our approach requires a significantly less complex model and less training data, yet it is superior to existing methods in the task of monocular depth estimation.
  arXiv  Detail & Related papers  (2022-04-14T16:14:37Z)
• Progressive Depth Learning for Single Image Dehazing [56.71963910162241]
  Existing dehazing methods often ignore the depth cues and fail in distant areas where heavier haze disturbs the visibility. We propose a deep end-to-end model that iteratively estimates image depths and transmission maps. Our approach benefits from explicitly modeling the inner relationship of image depth and transmission map, which is especially effective for distant hazy areas.
  arXiv  Detail & Related papers  (2021-02-21T05:24:18Z)
• Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces [103.08512487830669]
  This paper presents an uncalibrated deep neural network framework for the photometric stereo problem. Existing neural network-based methods either require exact light directions or ground-truth surface normals of the object or both. We propose an uncalibrated neural inverse rendering approach to this problem.
  arXiv  Detail & Related papers  (2020-12-12T10:33:08Z)
• SAFENet: Self-Supervised Monocular Depth Estimation with Semantic-Aware Feature Extraction [27.750031877854717]
  We propose SAFENet that is designed to leverage semantic information to overcome the limitations of the photometric loss. Our key idea is to exploit semantic-aware depth features that integrate the semantic and geometric knowledge. Experiments on KITTI dataset demonstrate that our methods compete or even outperform the state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-10-06T17:22:25Z)
• Adaptive confidence thresholding for monocular depth estimation [83.06265443599521]
  We propose a new approach to leverage pseudo ground truth depth maps of stereo images generated from self-supervised stereo matching methods. The confidence map of the pseudo ground truth depth map is estimated to mitigate performance degeneration by inaccurate pseudo depth maps. Experimental results demonstrate superior performance to state-of-the-art monocular depth estimation methods.
  arXiv  Detail & Related papers  (2020-09-27T13:26:16Z)
• Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images [59.906948203578544]
  We introduce a novel learning-based method to reconstruct the high-quality geometry and complex, spatially-varying BRDF of an arbitrary object. We first estimate per-view depth maps using a deep multi-view stereo network. These depth maps are used to coarsely align the different views. We propose a novel multi-view reflectance estimation network architecture.
  arXiv  Detail & Related papers  (2020-03-27T21:28:54Z)

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.