paper-with-me

홈 › Papers

LLA-FLOW: A Lightweight Local Aggregation on Cost Volume for Optical Flow Estimation

2023-04-17 · Jiawei Xu, Zongqing Lu, Qingmin Liao

Lack of texture often causes ambiguity in matching, and handling this issue is an important challenge in optical flow estimation. Some methods insert stacked transformer modules that allow the network to use global information of cost volume for estimation. But the global information aggregation often incurs serious memory and time costs during training and inference, which hinders model deployment. We draw inspiration from the traditional local region constraint and design the local similarity aggregation (LSA) and the shifted local similarity aggregation (SLSA). The aggregation for cost volume is implemented with lightweight modules that act on the feature maps. Experiments on the final pass of Sintel show the lower cost required for our approach while maintaining competitive performance.

📄 PDF Abstract BibTeX arXiv:2304.08101

Code (0)

등록된 구현이 없습니다.

Tasks

Optical Flow Estimation

Similar Papers 제목 키워드 기반

Separable Flow: Learning Motion Cost Volumes for Optical Flow Estimation

2021-01-01 · ICCV 2021 10 · Feihu Zhang, Oliver J. Woodford, Victor Adrian Prisacariu, Philip H.S. Torr

Full-motion cost volumes play a central role in current state-of-the-art optical flow methods. However, constructed using simple feature correlations, they lack the ability to encapsulate prior, or even non-local, kn…

Optical Flow Estimation

Explicit Motion Disentangling for Efficient Optical Flow Estimation

2023-01-01 · ICCV 2023 1 · Changxing Deng, Ao Luo, Haibin Huang, Shaodan Ma 외

In this paper, we propose a novel framework for optical flow estimation that achieves a good balance between performance and efficiency. Our approach involves disentangling global motion learning from local flow esti…

DecoderMotion EstimationOptical Flow Estimation

Ghost-Stereo: GhostNet-based Cost Volume Enhancement and Aggregation for Stereo Matching Networks

2024-05-23 · Xingguang Jiang, Xiaofeng Bian, Chenggang Guo

Depth estimation based on stereo matching is a classic but popular computer vision problem, which has a wide range of real-world applications. Current stereo matching methods generally adopt the deep Siamese neural netwo…

Depth EstimationStereo Matching

LightStereo: Channel Boost Is All Your Need for Efficient 2D Cost Aggregation

2024-06-28 · Xianda Guo, Chenming Zhang, Youmin Zhang, Wenzhao Zheng 외

We present LightStereo, a cutting-edge stereo-matching network crafted to accelerate the matching process. Departing from conventional methodologies that rely on aggregating computationally intensive 4D costs, LightStere…

AllStereo Matching

Decoupling Bidirectional Geometric Representations of 4D cost volume with 2D convolution

2025-09-02 · Xiaobao Wei, Changyong Shu, Zhaokun Yue, Chang Huang 외 arxiv

High-performance real-time stereo matching methods invariably rely on 3D regularization of the cost volume, which is unfriendly to mobile devices. And 2D regularization based methods struggle in ill-posed regions. In thi…