paper-with-me

홈 › Papers

Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint

2022-12-06 · Hai Jiang, Haipeng Li, Yuhang Lu, Songchen Han, Shuaicheng Liu

Homography estimation is erroneous in the case of large-baseline due to the low image overlay and limited receptive field. To address it, we propose a progressive estimation strategy by converting large-baseline homography into multiple intermediate ones, cumulatively multiplying these intermediate items can reconstruct the initial homography. Meanwhile, a semi-supervised homography identity loss, which consists of two components: a supervised objective and an unsupervised objective, is introduced. The first supervised loss is acting to optimize intermediate homographies, while the second unsupervised one helps to estimate a large-baseline homography without photometric losses. To validate our method, we propose a large-scale dataset that covers regular and challenging scenes. Experiments show that our method achieves state-of-the-art performance in large-baseline scenes while keeping competitive performance in small-baseline scenes. Code and dataset are available at https://github.com/megvii-research/LBHomo.

📄 PDF Abstract BibTeX arXiv:2212.02763

Code (1)

megvii-research/lbhomo 공식 구현 pytorch

Tasks

Homography Estimation

Similar Papers 제목 키워드 기반

InterNet: Unsupervised Cross-modal Homography Estimation Based on Interleaved Modality Transfer and Self-supervised Homography Prediction

2024-09-26 · Junchen Yu, Si-Yuan Cao, Runmin Zhang, Chenghao Zhang 외

We propose a novel unsupervised cross-modal homography estimation framework, based on interleaved modality transfer and self-supervised homography prediction, named InterNet. InterNet integrates modality transfer and sel…

Domain GeneralizationHomography Estimation

SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization

2025-01-01 · CVPR 2025 1 · Junchen Yu, Si-Yuan Cao, Runmin Zhang, Chenghao Zhang 외

We propose a novel unsupervised cross-modal homography estimation learning framework, named Split Supervised Homography estimation Network (SSHNet). SSHNet reformulates the unsupervised cross-modal homography estimat…

Domain GeneralizationHomography Estimation

AbHE: All Attention-based Homography Estimation

2022-12-06 · Mingxiao Huo, Zhihao Zhang, Xinyang Ren, Xianqiang Yang

Homography estimation is a basic computer vision task, which aims to obtain the transformation from multi-view images for image alignment. Unsupervised learning homography estimation trains a convolution neural network f…

AllHomography Estimationregression

Perceptual Loss for Robust Unsupervised Homography Estimation

2021-04-20 · Daniel Koguciuk, Elahe Arani, Bahram Zonooz

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 bidirectiona…

Dataset GenerationHomography EstimationRepresentation Learning

SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning

2024-07-11 · Runmin Zhang, Jun Ma, Si-Yuan Cao, Lun Luo 외

We propose a novel unsupervised cross-modal homography estimation framework based on intra-modal Self-supervised learning, Correlation, and consistent feature map Projection, namely SCPNet. The concept of intra-modal sel…

Homography EstimationSelf-Supervised Learning