NeuFlow v2: Push High-Efficiency Optical Flow To the Limit
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908476097167360 |
|---|---|
| author | Zhang, Zhiyong Gupta, Aniket Jiang, Huaizu Singh, Hanumant |
| author_facet | Zhang, Zhiyong Gupta, Aniket Jiang, Huaizu Singh, Hanumant |
| contents | Real-time high-accuracy optical flow estimation is critical for a variety of real-world robotic applications. However, current learning-based methods often struggle to balance accuracy and computational efficiency: methods that achieve high accuracy typically demand substantial processing power, while faster approaches tend to sacrifice precision. These fast approaches specifically falter in their generalization capabilities and do not perform well across diverse real-world scenarios. In this work, we revisit the limitations of the SOTA methods and present NeuFlow-V2, a novel method that offers both - high accuracy in real-world datasets coupled with low computational overhead. In particular, we introduce a novel light-weight backbone and a fast refinement module to keep computational demands tractable while delivering accurate optical flow. Experimental results on synthetic and real-world datasets demonstrate that NeuFlow-V2 provides similar accuracy to SOTA methods while achieving 10x-70x speedups. It is capable of running at over 20 FPS on 512x384 resolution images on a Jetson Orin Nano. The full training and evaluation code is available at https://github.com/neufieldrobotics/NeuFlow_v2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10161 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NeuFlow v2: Push High-Efficiency Optical Flow To the Limit Zhang, Zhiyong Gupta, Aniket Jiang, Huaizu Singh, Hanumant Computer Vision and Pattern Recognition Artificial Intelligence Robotics Real-time high-accuracy optical flow estimation is critical for a variety of real-world robotic applications. However, current learning-based methods often struggle to balance accuracy and computational efficiency: methods that achieve high accuracy typically demand substantial processing power, while faster approaches tend to sacrifice precision. These fast approaches specifically falter in their generalization capabilities and do not perform well across diverse real-world scenarios. In this work, we revisit the limitations of the SOTA methods and present NeuFlow-V2, a novel method that offers both - high accuracy in real-world datasets coupled with low computational overhead. In particular, we introduce a novel light-weight backbone and a fast refinement module to keep computational demands tractable while delivering accurate optical flow. Experimental results on synthetic and real-world datasets demonstrate that NeuFlow-V2 provides similar accuracy to SOTA methods while achieving 10x-70x speedups. It is capable of running at over 20 FPS on 512x384 resolution images on a Jetson Orin Nano. The full training and evaluation code is available at https://github.com/neufieldrobotics/NeuFlow_v2. |
| title | NeuFlow v2: Push High-Efficiency Optical Flow To the Limit |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2408.10161 |