WAFT: Warping-Alone Field Transforms for Optical Flow
Yihan Wang, Jia Deng
摘要
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. This design challenges the conventional wisdom that constructing cost volumes is necessary for strong performance. WAFT is a simple and flexible meta-architecture with minimal inductive biases and reliance on custom designs. Compared with existing methods, WAFT ranks 1st on Spring, Sintel, and KITTI benchmarks, achieves the best zero-shot generalization on KITTI, while being 1.3 -4.1× faster than existing methods that have competitive accuracy (e.g., 1.3× than Flowformer++, 4.1× than CCMR+). Code and model weights are available at https://github.com/princeton-vl/WAFT .
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper5
- CoWTracker: Tracking by Warping instead of CorrelationZihang Lai, Eldar Insafutdinov, Edgar Sucar, Andrea VedaldiCVPR 2026 · 被引用 12 次
- Efficient All-Pairs Correlation Volume Sampling for Optical Flow EstimationKarlis Martins Briedis, Markus Gross, Christopher SchroersCVPR 2026 · 被引用 1 次
- RetimeGS: Continuous-Time Reconstruction of 4D Gaussian SplattingXuezhen Wang, Li Ma, Yulin Shen, Zeyu Wang 等CVPR 2026
- Learning to Generate Highly Dynamic Videos using Synthetic Motion DataWonjoon Jin, Jiyun Won, Janghyeok Han, Qi Dai 等CVPR 2026
- ARFlow: Auto-regressive Optical Flow Estimation for Arbitrary-Length Videos via Progressive Next-Frame ForecastingJiuming Liu, Mengmeng Liu, Siting Zhu, Yunpeng Zhang 等ICLR 2026
它引用的顶会 Paper29
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn 等ICLR 2021 · 被引用 21,477 次
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao 等ICCV 2023 · 被引用 13,211 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Vision Transformers for Dense PredictionRené Ranftl, Alexey Bochkovskiy, Vladlen KoltunICCV 2021 · 被引用 2,647 次
- Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao 等NeurIPS 2024 · 被引用 2,305 次
相关 Paper
- GMFlow: Learning Optical Flow via Global MatchingHaofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi 等CVPR 2022 · 被引用 353 次
- FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion BasesMatteo Poggi, Fabio TosiICCV 2025 · 被引用 5 次
- CRAFT: Cross-Attentional Flow Transformer for Robust Optical FlowXiuchao Sui, Shaohua Li, Xue Geng, Yan Wu 等CVPR 2022 · 被引用 114 次
- FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow EstimationXiaoyu Shi, Zhaoyang Huang, Dasong Li, Manyuan Zhang 等CVPR 2023
- MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow EstimationVladislav Bargatin, Egor Chistov, Alexander Yakovenko, Dmitriy S. VatolinICCV 2025 · 被引用 11 次
