Perceptual Loss for Robust Unsupervised Homography Estimation

• URL: http://arxiv.org/abs/2104.10011v1
• Date: Tue, 20 Apr 2021 14:41:54 GMT
• Title: Perceptual Loss for Robust Unsupervised Homography Estimation
• Authors: Daniel Koguciuk, Elahe Arani, Bahram Zonooz
• Abstract summary: BiHomE minimizes the distance in the feature space between the warped image from the source viewpoint and the corresponding image from the target viewpoint. We show that biHomE achieves state-of-the-art performance on synthetic COCO dataset, which is also comparable or better compared to supervised approaches.
• Score: 1.2891210250935146
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Homography estimation is often an indispensable step in many computer vision tasks. The existing approaches, however, are not robust to illumination and/or larger viewpoint changes. In this paper, we propose bidirectional implicit Homography Estimation (biHomE) loss for unsupervised homography estimation. biHomE minimizes the distance in the feature space between the warped image from the source viewpoint and the corresponding image from the target viewpoint. Since we use a fixed pre-trained feature extractor and the only learnable component of our framework is the homography network, we effectively decouple the homography estimation from representation learning. We use an additional photometric distortion step in the synthetic COCO dataset generation to better represent the illumination variation of the real-world scenarios. We show that biHomE achieves state-of-the-art performance on synthetic COCO dataset, which is also comparable or better compared to supervised approaches. Furthermore, the empirical results demonstrate the robustness of our approach to illumination variation compared to existing methods.

Related papers

• Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
  Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data. Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
  arXiv  Detail & Related papers  (2024-03-23T22:32:06Z)
• RANRAC: Robust Neural Scene Representations via Random Ray Consensus [12.161889666145127]
  RANdom RAy Consensus (RANRAC) is an efficient approach to eliminate the effect of inconsistent data. We formulate a fuzzy adaption of the RANSAC paradigm, enabling its application to large scale models. Results indicate significant improvements compared to state-of-the-art robust methods for novel-view synthesis.
  arXiv  Detail & Related papers  (2023-12-15T13:33:09Z)
• View Consistent Purification for Accurate Cross-View Localization [59.48131378244399]
  This paper proposes a fine-grained self-localization method for outdoor robotics. The proposed method addresses limitations in existing cross-view localization methods. It is the first sparse visual-only method that enhances perception in dynamic environments.
  arXiv  Detail & Related papers  (2023-08-16T02:51:52Z)
• Breaking Modality Disparity: Harmonized Representation for Infrared and Visible Image Registration [66.33746403815283]
  We propose a scene-adaptive infrared and visible image registration. We employ homography to simulate the deformation between different planes. We propose the first ground truth available misaligned infrared and visible image dataset.
  arXiv  Detail & Related papers  (2023-04-12T06:49:56Z)
• Unsupervised Light Field Depth Estimation via Multi-view Feature Matching with Occlusion Prediction [15.421219881815956]
  It is costly to obtain sufficient depth labels for supervised training. In this paper, we propose an unsupervised framework to estimate depth from LF images.
  arXiv  Detail & Related papers  (2023-01-20T06:11:17Z)
• FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation [17.572459787107427]
  We propose a flow distillation loss to replace the typical photometric loss and a prior flow based mask to remove invalid pixels. Our approach achieves state-of-the-art results on both KITTI and NYU-Depth-v2 datasets.
  arXiv  Detail & Related papers  (2023-01-20T04:02:13Z)
• 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)
• Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior [40.61944814314655]
  We propose an unsupervised low-light image enhancement method based on an effective prior histogram termed equalization prior (HEP) We introduce a Noise Disentanglement Module (NDM) to disentangle the noise and content in the reflectance maps with the reliable aid of unpaired clean images. Our method performs favorably against the state-of-the-art unsupervised low-light enhancement algorithms and even matches the state-of-the-art supervised algorithms.
  arXiv  Detail & Related papers  (2021-12-03T07:51:08Z)
• Low-resolution Human Pose Estimation [49.531572116079026]
  We propose a novel Confidence-Aware Learning (CAL) method for low-resolution pose estimation. CAL addresses two fundamental limitations of existing offset learning methods: inconsistent training and testing, decoupled heatmap and offset learning. Our method outperforms significantly the state-of-the-art methods for low-resolution human pose estimation.
  arXiv  Detail & Related papers  (2021-09-19T09:13:57Z)
• Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection [27.68752841842823]
  We introduce a new framework for unsupervised deep homography estimation. We show that our approach outperforms the state-of-the-art on the homography benchmark datasets.
  arXiv  Detail & Related papers  (2021-03-29T05:51:34Z)
• Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo [61.6260594326246]
  We introduce an efficient fully-convolutional architecture that can leverage both spatial and photometric context simultaneously. Using separable 4D convolutions and 2D heat-maps reduces the size and makes more efficient.
  arXiv  Detail & Related papers  (2021-03-22T18:06:58Z)

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.