|
Canada-0-CARTAGE ไดเรกทอรีที่ บริษัท
|
ข่าว บริษัท :
- WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
Recently, WAFT [wang2025waft], a new state-of-art optical flow estimator, demonstrates that cost volumes can be replaced by high-resolution feature-space warping, leading to a substantially simpler design and improved accuracy and efficiency This raises a natural question: can cost volumes be replaced by warping also for stereo matching?
- WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
Join the discussion on this paper page WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
- [ICLR2026 - Oral] WAFT: Warping-Alone Field Transforms for . . . - GitHub
We introduce Warping-Alone Field Transforms (WAFT), a simple and effective method for optical flow WAFT is similar to RAFT but replaces cost volume with high-resolution warping, achieving better accuracy with lower memory cost
- WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
We introduce WAFT-Stereo, a simple and effective warping-based method for stereo matching WAFT-Stereo demonstrates that cost volumes, a common design used in many leading methods, are not necessary for strong performance and can be replaced by warping with improved efficiency
- WAFT: Warping-Alone Field Transforms for Optical Flow
We introduce Warping-Alone Field Transforms (WAFT), a simple and effective method for optical flow WAFT is similar to RAFT but replaces cost volume with high-resolution warping, achieving better accuracy with lower memory cost
- WAFT: Warping-Alone Field Transforms for Optical Flow
WAFT-Stereo demonstrates that cost volumes are not necessary for strong performance and can be replaced by warping with improved efficiency, and ranks first on ETH3D, KITTI and Middlebury public benchmarks
- Vision Learning Lab @ Princeton University
2026 What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching? David Yan, Alexander Raistrick, Jia Deng IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026 [ paper ] [ code ] SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping Hongyu Wen, Jia Deng
- GitHub Pages - Yihan Wangs Homepage
I work on geometric vision, with a particular focus on wide-baseline matching My work has been recognized with honors, including a best paper nomination at ECCV 2024
- WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
We introduce WAFT-Stereo, a simple and effective warping-based method for stereo matching WAFT-Stereo demonstrates that cost volumes, a common design used in many leading methods, are not necessary for strong performance and can be replaced by warping with improved efficiency
- WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
We introduce WAFT-Stereo, a simple and effective warping-based method for stereo matching WAFT-Stereo demonstrates that cost volumes, a common design used in many leading methods, are not nec-essary for strong performance and can be replaced by warping with improved efficiency
|
|