Paper Detail

WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching

Yihan Wang, Jia Deng

huggingface Score 6.8

Published 2026-03-25 · First seen 2026-03-28

General AI

Abstract

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 ranks first on ETH3D, KITTI and Middlebury public benchmarks, reducing the zero-shot error by 81% on ETH3D benchmark, while being 1.8-6.7x faster than competitive methods. Code and model weights are available at https://github.com/princeton-vl/WAFT-Stereo.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{wang2026waft,
  title = {WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching},
  author = {Yihan Wang and Jia Deng},
  year = {2026},
  abstract = {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 ranks first on ETH3D, KITTI and Middlebury public benchmarks, reducing the zero-shot error by 81\% on ETH3D benchmark, while being 1.8-6.7x faster than competitive methods. Code and model weights are available },
  url = {https://huggingface.co/papers/2603.24836},
  keywords = {stereo matching, cost volumes, warping, ETH3D, KITTI, Middlebury, code available, huggingface daily},
  eprint = {2603.24836},
  archiveprefix = {arXiv},
}

Metadata

{}