paper-with-me

홈 › Papers

Unsupervised Flow Refinement near Motion Boundaries

2022-08-03 · Shuzhi Yu, Hannah Halin Kim, Shuai Yuan, Carlo Tomasi

Unsupervised optical flow estimators based on deep learning have attracted increasing attention due to the cost and difficulty of annotating for ground truth. Although performance measured by average End-Point Error (EPE) has improved over the years, flow estimates are still poorer along motion boundaries (MBs), where the flow is not smooth, as is typically assumed, and where features computed by neural networks are contaminated by multiple motions. To improve flow in the unsupervised settings, we design a framework that detects MBs by analyzing visual changes along boundary candidates and replaces motions close to detections with motions farther away. Our proposed algorithm detects boundaries more accurately than a baseline method with the same inputs and can improve estimates from any flow predictor without additional training.

📄 PDF Abstract BibTeX arXiv:2208.02305

Code (0)

등록된 구현이 없습니다.

Tasks

Optical Flow Estimation

Similar Papers 제목 키워드 기반

SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving

2023-03-10 · ICCV 2023 1 · Shuai Yuan, Shuzhi Yu, Hannah Kim, Carlo Tomasi

Unsupervised optical flow estimation is especially hard near occlusions and motion boundaries and in low-texture regions. We show that additional information such as semantics and domain knowledge can help better constra…

Autonomous DrivingOptical Flow EstimationSemantic Segmentation

Deep Motion Boundary Detection

2018-04-13 · Xiaoqing Yin, Xiyang Dai, Xinchao Wang, Maojun Zhang 외

Motion boundary detection is a crucial yet challenging problem. Prior methods focus on analyzing the gradients and distributions of optical flow fields, or use hand-crafted features for motion boundary learning. In this …

Boundary DetectionOptical Flow Estimation

What's in the Flow? Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detection

2024-02-15 · IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 1 · Sourabh Vasant Gothe, Vibhav Agarwal, Sourav Ghosh, Jayesh Rajkumar Vachhani 외

Generic Event Boundary Detection (GEBD) task aims to recognize generic, taxonomy-free boundaries that segment a video into meaningful events. Current methods typically involve a neural model trained on a large volume of …

Boundary DetectionGeneric Event Boundary DetectionOptical Flow Estimation

Unsupervised motion saliency map estimation based on optical flow inpainting

2019-03-12 · L. Maczyta, P. Bouthemy, O. Le Meur

The paper addresses the problem of motion saliency in videos, that is, identifying regions that undergo motion departing from its context. We propose a new unsupervised paradigm to compute motion saliency maps. The key i…

Optical Flow Estimation

UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model

2024-05-04 · CVPR 2024 1 · Shuai Yuan, Lei Luo, Zhuo Hui, Can Pu 외

Traditional unsupervised optical flow methods are vulnerable to occlusions and motion boundaries due to lack of object-level information. Therefore, we propose UnSAMFlow, an unsupervised flow network that also leverages …

ObjectOptical Flow Estimation