Raft: Recurrent all-pairs field transforms for optical flow

Z Teed, J Deng - Computer Vision–ECCV 2020: 16th European …, 2020‏ - Springer
Abstract We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network
architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D …

Iterative residual refinement for joint optical flow and occlusion estimation

J Hur, S Roth - Proceedings of the IEEE/CVF conference on …, 2019‏ - openaccess.thecvf.com
Deep learning approaches to optical flow estimation have seen rapid progress over the
recent years. One common trait of many networks is that they refine an initial flow estimate …

Separable flow: Learning motion cost volumes for optical flow estimation

F Zhang, OJ Woodford… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
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 …

Sdc-stacked dilated convolution: A unified descriptor network for dense matching tasks

R Schuster, O Wasenmuller… - Proceedings of the …, 2019‏ - openaccess.thecvf.com
Dense pixel matching is important for many computer vision tasks such as disparity and flow
estimation. We present a robust, unified descriptor network that considers a large context …

Continual occlusion and optical flow estimation

M Neoral, J Šochman, J Matas - Asian conference on computer vision, 2018‏ - Springer
Two optical flow estimation problems are addressed:(i) occlusion estimation and handling,
and (ii) estimation from image sequences longer than two frames. The proposed …

Parallel multiscale context-based edge-preserving optical flow estimation with occlusion detection

C Zhang, C Feng, Z Chen, W Hu, M Li - Signal Processing: Image …, 2022‏ - Elsevier
Although convolutional neural network (CNN)-based optical flow approaches have exhibited
good performance in terms of computational accuracy and efficiency in recent years, the …

Attentive multimodal fusion for optical and scene flow

Y Zhou, G Mei, Y Wang, F Poiesi… - IEEE Robotics and …, 2023‏ - ieeexplore.ieee.org
This letter presents an investigation into the estimation of optical and scene flow using
RGBD information in scenarios where the RGB modality is affected by noise or captured in …

SceneFlowFields++: Multi-frame matching, visibility prediction, and robust interpolation for scene flow estimation

R Schuster, O Wasenmüller, C Unger, G Kuschk… - International journal of …, 2020‏ - Springer
State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time,
and robustness. With the successful concept of pixel-wise matching and sparse-to-dense …

[کتاب][B] Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II

A Vedaldi, H Bischof, T Brox, JM Frahm - 2020‏ - books.google.com
The 30-volume set, comprising the LNCS books 12346 until 12375, constitutes the refereed
proceedings of the 16th European Conference on Computer Vision, ECCV 2020, which was …

Efficient motion feature aggregation for optical flow via locality-sensitive hashing

W Chen, Z Liu, X Wu, Z Liu, Z Li - Neurocomputing, 2025‏ - Elsevier
Optical flow estimation aims to find the 2D motion field by identifying the corresponding
pixels between two images. With the tremendous progress of deep learning, previous works …