Author : Philippe Weinzaepfel, Thomas Lucas, Vincent Leroy, Yohann Cabon, Vaibhav Arora, Romain Brgier, Gabriela Csurka, Leonid Antsfeld, Boris Chidlovskii, Jrme Revaud

Abstract : Despite impressive performance for high-level downstream tasks, self-supervised pre-training methods have not yet fully delivered on dense geometric vision tasks such as stereo matching or optical flow. The application of selfsupervised concepts, such as instance discrimination or masked image modeling, to geometric tasks is an active area of research. In this work, we build on the recent crossview completion framework, a variation of masked image modeling that leverages a second view from the same scene which makes it well suited for binocular downstream tasks. The applicability of this concept has so far been limited in at least two ways: (a) by the difficulty of collecting realworld image pairs in practice only synthetic data have been used and (b) by the lack of generalization of vanilla transformers to dense downstream tasks for which relative position is more meaningful than absolute position. We explore three avenues of improvement: first, we introduce a method to collect suitable real-world image pairs at large scale. Second, we experiment with relative positional embeddings and show that they enable vision transformers to perform substantially better. Third, we scale up vision transformer based cross-completion architectures, which is made possible by the use of large amounts of data. With these improvements, we show for the first time that stateof-the-art results on stereo matching and optical flow can be reached without using any classical task-specific techniques like correlation volume, iterative estimation, image warping or multi-scale reasoning, thus paving the way towards universal vision models.

2. Self-Supervised Intensity-Event Stereo Matching(arXiv)

Author : Jinjin Gu, Jinan Zhou, Ringo Sai Wo Chu, Yan Chen, Jiawei Zhang, Xuanye Cheng, Song Zhang, Jimmy S. Ren

Abstract : Event cameras are novel bio-inspired vision sensors that output pixel-level intensity changes in microsecond accuracy with a high dynamic range and low power consumption. Despite these advantages, event cameras cannot be directly applied to computational imaging tasks due to the inability to obtain high-quality intensity and events simultaneously. This paper aims to connect a standalone event camera and a modern intensity camera so that the applications can take advantage of both two sensors. We establish this connection through a multi-modal stereo matching task. We first convert events to a reconstructed image and extend the existing stereo networks to this multi-modality condition. We propose a self-supervised method to train the multi-modal stereo network without using ground truth disparity data. The structure loss calculated on image gradients is used to enable self-supervised learning on such multi-modal data. Exploiting the internal stereo constraint between views with different modalities, we introduce general stereo loss functions, including disparity cross-consistency loss and internal disparity loss, leading to improved performance and robustness compared to existing approaches. The experiments demonstrate the effectiveness of the proposed method, especially the proposed general stereo loss functions, on both synthetic and real datasets. At last, we shed light on employing the aligned events and intensity images in downstream tasks, e.g., video interpolation application.

Read the original:

Use cases of Stereo Matching part7(Machine Learning + AI) - Medium