Related papers: Unsupervised Flow Refinement near Motion Boundaries

Unsupervised Flow Refinement near Motion Boundaries

URL: http://arxiv.org/abs/2208.02305v1
Date: Wed, 3 Aug 2022 18:44:39 GMT
Title: Unsupervised Flow Refinement near Motion Boundaries
Authors: Shuzhi Yu, Hannah Halin Kim, Shuai Yuan, Carlo Tomasi
Abstract summary: Unsupervised optical flow estimators based on deep learning have attracted increasing attention due to the cost and difficulty of annotating for ground truth. 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.
Score: 3.5317804902980527
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: 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.

Related papers

Robust Optical Flow Computation: A Higher-Order Differential Approach [0.0]
This research proposes an innovative algorithm for optical flow computation, utilizing the higher precision of second-order Taylor series approximation. An impressive showcase of the algorithm's capabilities emerges through its performance on optical flow benchmarks such as KITTI and Middlebury.
arXiv Detail & Related papers (2024-10-12T15:20:11Z)
OptFlow: Fast Optimization-based Scene Flow Estimation without Supervision [6.173968909465726]
We present OptFlow, a fast optimization-based scene flow estimation method. It achieves state-of-the-art performance for scene flow estimation on popular autonomous driving benchmarks.
arXiv Detail & Related papers (2024-01-04T21:47:56Z)
AccFlow: Backward Accumulation for Long-Range Optical Flow [70.4251045372285]
This paper proposes a novel recurrent framework called AccFlow for long-range optical flow estimation. We demonstrate the superiority of backward accumulation over conventional forward accumulation. Experiments validate the effectiveness of AccFlow in handling long-range optical flow estimation.
arXiv Detail & Related papers (2023-08-25T01:51:26Z)
The Cascaded Forward Algorithm for Neural Network Training [61.06444586991505]
We propose a new learning framework for neural networks, namely Cascaded Forward (CaFo) algorithm, which does not rely on BP optimization as that in FF. Unlike FF, our framework directly outputs label distributions at each cascaded block, which does not require generation of additional negative samples. In our framework each block can be trained independently, so it can be easily deployed into parallel acceleration systems.
arXiv Detail & Related papers (2023-03-17T02:01:11Z)
SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving [5.342413115295559]
We introduce SemARFlow, an unsupervised optical flow network designed for autonomous driving data. We show visible improvements around object boundaries as well as a greater ability to generalize across datasets.
arXiv Detail & Related papers (2023-03-10T21:17:14Z)
Deep Equilibrium Optical Flow Estimation [80.80992684796566]
Recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms. These RNNs impose large computation and memory overheads, and are not directly trained to model such stable estimation. We propose deep equilibrium (DEQ) flow estimators, an approach that directly solves for the flow as the infinite-level fixed point of an implicit layer.
arXiv Detail & Related papers (2022-04-18T17:53:44Z)
Unsupervised Motion Representation Enhanced Network for Action Recognition [4.42249337449125]
Motion representation between consecutive frames has proven to have great promotion to video understanding. TV-L1 method, an effective optical flow solver, is time-consuming and expensive in storage for caching the extracted optical flow. We propose UF-TSN, a novel end-to-end action recognition approach enhanced with an embedded lightweight unsupervised optical flow estimator.
arXiv Detail & Related papers (2021-03-05T04:14:32Z)
A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries [62.28265459308354]
Network learns end-to-end mapping between spatial positions and CFD quantities. Incompress laminar steady flow past a cylinder with various shapes for its cross section is considered. Network predicts the flow fields hundreds of times faster than our conventional CFD.
arXiv Detail & Related papers (2020-10-15T12:15:02Z)
What Matters in Unsupervised Optical Flow [51.45112526506455]
We compare and analyze a set of key components in unsupervised optical flow. We construct a number of novel improvements to unsupervised flow models. We present a new unsupervised flow technique that significantly outperforms the previous state-of-the-art.
arXiv Detail & Related papers (2020-06-08T19:36:26Z)
Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level Optimization [59.9673626329892]
We exploit the global relationship between optical flow and camera motion using epipolar geometry. We use implicit differentiation to enable back-propagation through the lower-level geometric optimization layer independent of its implementation.
arXiv Detail & Related papers (2020-02-26T22:28:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.