CodingHomo: Bootstrapping Deep Homography With Video Coding

Abstract

Homography estimation is a fundamental task in computer vision with applications in diverse fields. Recent advances in deep learning have improved homography estimation, particularly with unsupervised learning approaches, offering increased robustness and generalizability. However, accurately predicting homography, especially in complex motions, remains a challenge. In response, this work introduces a novel method leveraging video coding, particularly by harnessing inherent motion vectors (MVs) present in videos. We present CodingHomo, an unsupervised framework for homography estimation. Our framework features a Mask-Guided Fusion (MGF) module that identifies and utilizes beneficial features among the MVs, thereby enhancing the accuracy of homography prediction. Additionally, the Mask-Guided Homography Estimation (MGHE) module is presented for eliminating undesired features in the coarse-to-fine homography refinement process. CodingHomo outperforms existing state-of-the-art unsupervised methods, delivering good robustness and generalizability. The code and dataset are available at: \href{github}{https://github.com/liuyike422/CodingHomo

References in corpus (7)

• k-Nearest Neighbour Classifiers: 2nd Edition (with Python examples)
• M-LVC: Multiple Frames Prediction for Learned Video Compression
• Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration
• Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation
• GL-RG: Global-Local Representation Granularity for Video Captioning
• GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning
• Homography-based Visual Servoing with Remote Center of Motion for Semi-autonomous Robotic Endoscope Manipulation