no code implementations • 6 Mar 2024 • Gangwei Xu, Yujin Wang, Jinwei Gu, Tianfan Xue, Xin Yang
HDRFlow has three novel designs: an HDR-domain alignment loss (HALoss), an efficient flow network with a multi-size large kernel (MLK), and a new HDR flow training scheme.
1 code implementation • 1 Mar 2024 • Xianqi Wang, Gangwei Xu, Hao Jia, Xin Yang
Stereo matching methods based on iterative optimization, like RAFT-Stereo and IGEV-Stereo, have evolved into a cornerstone in the field of stereo matching.
no code implementations • 28 Dec 2023 • Miaojie Feng, Longliang Liu, Hao Jia, Gangwei Xu, Xin Yang
This paper introduces FlowDA, an unsupervised domain adaptive (UDA) framework for optical flow estimation.
no code implementations • 6 Dec 2023 • Gangwei Xu, Shujun Chen, Hao Jia, Miaojie Feng, Xin Yang
The full 4D cost volume in Recurrent All-Pairs Field Transforms (RAFT) or global matching by Transformer achieves impressive performance for optical flow estimation.
1 code implementation • 4 Nov 2023 • Miaojie Feng, Junda Cheng, Hao Jia, Longliang Liu, Gangwei Xu, Qingyong Hu, Xin Yang
This architecture mitigates the multi-peak distribution problem in matching through the multi-peak lookup strategy, and integrates the coarse-to-fine concept into the iterative framework via the cascade search range.
1 code implementation • CVPR 2023 • Gangwei Xu, Xianqi Wang, Xiaohuan Ding, Xin Yang
The proposed IGEV-Stereo builds a combined geometry encoding volume that encodes geometry and context information as well as local matching details, and iteratively indexes it to update the disparity map.
1 code implementation • 7 Jan 2023 • Gangwei Xu, Huan Zhou, Xin Yang
In this paper, we propose CGI-Stereo, a novel neural network architecture that can concurrently achieve real-time performance, competitive accuracy, and strong generalization ability.
3 code implementations • 23 Sep 2022 • Gangwei Xu, Yun Wang, Junda Cheng, Jinhui Tang, Xin Yang
In this paper, we present a novel cost volume construction method, named attention concatenation volume (ACV), which generates attention weights from correlation clues to suppress redundant information and enhance matching-related information in the concatenation volume.
2 code implementations • CVPR 2022 • Gangwei Xu, Junda Cheng, Peng Guo, Xin Yang
Stereo matching is a fundamental building block for many vision and robotics applications.
Ranked #1 on Stereo Depth Estimation on Spring