Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection

• URL: http://arxiv.org/abs/2103.15346v1
• Date: Mon, 29 Mar 2021 05:51:34 GMT
• Title: Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection
• Authors: Nianjin Ye, Chuan Wang, Haoqiang Fan, Shuaicheng Liu
• Abstract summary: 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.
• Score: 27.68752841842823
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we introduce a new framework for unsupervised deep homography estimation. Our contributions are 3 folds. First, unlike previous methods that regress 4 offsets for a homography, we propose a homography flow representation, which can be estimated by a weighted sum of 8 pre-defined homography flow bases. Second, considering a homography contains 8 Degree-of-Freedoms (DOFs) that is much less than the rank of the network features, we propose a Low Rank Representation (LRR) block that reduces the feature rank, so that features corresponding to the dominant motions are retained while others are rejected. Last, we propose a Feature Identity Loss (FIL) to enforce the learned image feature warp-equivariant, meaning that the result should be identical if the order of warp operation and feature extraction is swapped. With this constraint, the unsupervised optimization is achieved more effectively and more stable features are learned. Extensive experiments are conducted to demonstrate the effectiveness of all the newly proposed components, and results show our approach outperforms the state-of-the-art on the homography benchmark datasets both qualitatively and quantitatively.

Related papers

• Deep Homography Estimation for Visual Place Recognition [49.235432979736395]
  We propose a transformer-based deep homography estimation (DHE) network. It takes the dense feature map extracted by a backbone network as input and fits homography for fast and learnable geometric verification. Experiments on benchmark datasets show that our method can outperform several state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-02-25T13:22:17Z)
• Leveraging Graph Diffusion Models for Network Refinement Tasks [72.54590628084178]
  We propose a novel graph generative framework, SGDM, based on subgraph diffusion. Our framework not only improves the scalability and fidelity of graph diffusion models, but also leverages the reverse process to perform novel, conditional generation tasks.
  arXiv  Detail & Related papers  (2023-11-29T18:02:29Z)
• Few-shot Image Classification based on Gradual Machine Learning [6.935034849731568]
  Few-shot image classification aims to accurately classify unlabeled images using only a few labeled samples. We propose a novel approach based on the non-i.i.d paradigm of gradual machine learning (GML) We show that the proposed approach can improve the SOTA performance by 1-5% in terms of accuracy.
  arXiv  Detail & Related papers  (2023-07-28T12:30:41Z)
• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment [53.401889855278704]
  Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. We propose a two-stage background suppression and foreground alignment framework, which is composed of a background activation suppression (BAS) module, a foreground object alignment (FOA) module, and a local to local (L2L) similarity metric. Experiments conducted on multiple popular fine-grained benchmarks demonstrate that our method outperforms the existing state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2022-10-04T07:54:40Z)
• Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation [3.1869033681682124]
  This paper presents a novel scene flow estimation architecture using bidirectional flow embedding layers. The proposed bidirectional layer learns features along both forward and backward directions, enhancing the estimation performance. In addition, hierarchical feature extraction and warping improve the performance and reduce computational overhead.
  arXiv  Detail & Related papers  (2022-07-15T15:14:53Z)
• Abs-CAM: A Gradient Optimization Interpretable Approach for Explanation of Convolutional Neural Networks [7.71412567705588]
  Class activation mapping-based method has been widely used to interpret the internal decisions of models in computer vision tasks. We propose an Absolute value Class Activation Mapping-based (Abs-CAM) method, which optimize the gradients derived from the backpropagation. The framework of Abs-CAM is divided into two phases: generating initial saliency map and generating final saliency map.
  arXiv  Detail & Related papers  (2022-07-08T02:06:46Z)
• Unsupervised Homography Estimation with Coplanarity-Aware GAN [39.477228263736905]
  Estimating homography from an image pair is a fundamental problem in image alignment. HomoGAN is designed to guide unsupervised homography estimation to focus on the dominant plane. Results show that our matching error is 22% lower than the previous SOTA method.
  arXiv  Detail & Related papers  (2022-05-08T09:26:47Z)
• CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency [61.40511574314069]
  Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors.
  arXiv  Detail & Related papers  (2021-06-20T08:20:56Z)
• Perceptual Loss for Robust Unsupervised Homography Estimation [1.2891210250935146]
  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.
  arXiv  Detail & Related papers  (2021-04-20T14:41:54Z)
• Self-Supervised Tuning for Few-Shot Segmentation [82.32143982269892]
  Few-shot segmentation aims at assigning a category label to each image pixel with few annotated samples. Existing meta-learning method tends to fail in generating category-specifically discriminative descriptor when the visual features extracted from support images are marginalized in embedding space. This paper presents an adaptive framework tuning, in which the distribution of latent features across different episodes is dynamically adjusted based on a self-segmentation scheme.
  arXiv  Detail & Related papers  (2020-04-12T03:53:53Z)
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification [84.43394420267794]
  We propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. Our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.
  arXiv  Detail & Related papers  (2020-03-18T12:18:35Z)

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.