Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Yingping, Fu, Ying, Hu, Yutao, Shao, Wenqi, Liu, Jiaming, Zhang, Debing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913885451190272
author Liang, Yingping
Fu, Ying
Hu, Yutao
Shao, Wenqi
Liu, Jiaming
Zhang, Debing
author_facet Liang, Yingping
Fu, Ying
Hu, Yutao
Shao, Wenqi
Liu, Jiaming
Zhang, Debing
contents Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied to real-world applications and limits the benefits of scaling up datasets. To address these challenges, we propose \textbf{Flow-Anything}, a large-scale data generation framework designed to learn optical flow estimation from any single-view images in the real world. We employ two effective steps to make data scaling-up promising. First, we convert a single-view image into a 3D representation using advanced monocular depth estimation networks. This allows us to render optical flow and novel view images under a virtual camera. Second, we develop an Object-Independent Volume Rendering module and a Depth-Aware Inpainting module to model the dynamic objects in the 3D representation. These two steps allow us to generate realistic datasets for training from large-scale single-view images, namely \textbf{FA-Flow Dataset}. For the first time, we demonstrate the benefits of generating optical flow training data from large-scale real-world images, outperforming the most advanced unsupervised methods and supervised methods on synthetic datasets. Moreover, our models serve as a foundation model and enhance the performance of various downstream video tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_07740
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images
Liang, Yingping
Fu, Ying
Hu, Yutao
Shao, Wenqi
Liu, Jiaming
Zhang, Debing
Computer Vision and Pattern Recognition
Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied to real-world applications and limits the benefits of scaling up datasets. To address these challenges, we propose \textbf{Flow-Anything}, a large-scale data generation framework designed to learn optical flow estimation from any single-view images in the real world. We employ two effective steps to make data scaling-up promising. First, we convert a single-view image into a 3D representation using advanced monocular depth estimation networks. This allows us to render optical flow and novel view images under a virtual camera. Second, we develop an Object-Independent Volume Rendering module and a Depth-Aware Inpainting module to model the dynamic objects in the 3D representation. These two steps allow us to generate realistic datasets for training from large-scale single-view images, namely \textbf{FA-Flow Dataset}. For the first time, we demonstrate the benefits of generating optical flow training data from large-scale real-world images, outperforming the most advanced unsupervised methods and supervised methods on synthetic datasets. Moreover, our models serve as a foundation model and enhance the performance of various downstream video tasks.
title Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.07740