We introduce SEA-RAFT, a more simple, efficient, and accurate RAFT for optical flow.
Compared with RAFT, SEA-RAFT is trained with a new loss (mixture of Laplace). It directly …

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 …

Optical flow estimation a process of predicting pixel-wise displacement between consecutive
frames has commonly been approached as a regression task in the age of deep learning …

Detecting objects seamlessly blended into their surroundings represents a complex task for
both human cognitive capabilities and advanced artificial intelligence algorithms. Currently …

We study the problem of estimating optical flow from event cameras. One important issue is
how to build a high-quality event-flow dataset with accurate event values and flow labels …

The full 4D cost volume in Recurrent All-Pairs Field Transforms (RAFT) or global matching
by Transformer achieves impressive performance for optical flow estimation. However, their …

With the advent of deep learning methods performance and efficiency of optical flow
estimation has significantly increased especially for supervised models. However they do …

Lacking a large-scale dataset is the major obstacle limiting sign language recognition (SLR)
to work well in real-world scenarios. This is mainly due to the huge collection and annotation …

Abstract We propose the Multi-Head Gaussian Adaptive Attention Mechanism (GAAM), a
novel probabilistic attention framework, and the Gaussian Adaptive Transformer (GAT) …

Integral cameras cause motion blur during relative object displacement, leading to degraded
image aesthetics and reduced performance of image-based algorithms. Event cameras …