Related papers: TransFlow: Transformer as Flow Learner

End-to-end trained convolutional neural networks have led to a breakthrough in optical flow estimation. The most recent advances focus on improving the optical flow estimation by improving the architecture and setting a new benchmark on the…

Key-point-based scene understanding is fundamental for autonomous driving applications. At the same time, optical flow plays an important role in many vision tasks. However, due to the implicit bias of equal attention on all points, classic…

Real-time motion detection in non-stationary scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource. These challenges degrade the performance of the existing methods in…

Autonomous vehicle navigation is a key challenge in artificial intelligence, requiring robust and accurate decision-making processes. This research introduces a new end-to-end method that exploits multimodal information from a single…

Traditional discriminative computer vision relies predominantly on static projections, mapping input features to outputs in a single computational step. Although efficient, this paradigm lacks the iterative refinement and robustness…

Estimating the 3D motion of points in a scene, known as scene flow, is a core problem in computer vision. Traditional learning-based methods designed to learn end-to-end 3D flow often suffer from poor generalization. Here we present a…

Scene flow is the task of estimating 3D motion vectors to individual points of a dynamic 3D scene. Motion vectors have shown to be beneficial for downstream tasks such as action classification and collision avoidance. However, data…

Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels between two images. Despite the tremendous progress of deep learning-based optical flow methods, it remains a challenge to accurately estimate…

Modern optical flow methods are often composed of a cascade of many independent steps or formulated as a black box neural network that is hard to interpret and analyze. In this work we seek for a plain, interpretable, but learnable…

Previous dominant methods for scene flow estimation focus mainly on input from two consecutive frames, neglecting valuable information in the temporal domain. While recent trends shift towards multi-frame reasoning, they suffer from rapidly…

Occlusion is an inevitable and critical problem in unsupervised optical flow learning. Existing methods either treat occlusions equally as non-occluded regions or simply remove them to avoid incorrectness. However, the occlusion regions can…

Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…

Optical flow estimation is very challenging in situations with transparent or occluded objects. In this work, we address these challenges at the task level by introducing Amodal Optical Flow, which integrates optical flow with amodal…

As a bio-inspired sensor with high temporal resolution, the spiking camera has an enormous potential in real applications, especially for motion estimation in high-speed scenes. However, frame-based and event-based methods are not well…

Scene flow estimation is the task of describing 3D motion between temporally successive observations. This thesis aims to build the foundation for building scene flow estimators with two important properties: they are scalable, i.e. they…

We propose an optical flow-guided approach for semi-supervised video object segmentation. Optical flow is usually exploited as additional guidance information in unsupervised video object segmentation. However, its relevance in…

3D scene flow estimation from point clouds is a low-level 3D motion perception task in computer vision. Flow embedding is a commonly used technique in scene flow estimation, and it encodes the point motion between two consecutive frames.…

This paper presents an investigation of vision transformer learning for multi-view geometry tasks, such as optical flow estimation, by fine-tuning video foundation models. Unlike previous methods that involve custom architectural designs…

Over four decades, the majority addresses the problem of optical flow estimation using variational methods. With the advance of machine learning, some recent works have attempted to address the problem using convolutional neural network…

The occlusion problem remains a crucial challenge in optical flow estimation (OFE). Despite the recent significant progress brought about by deep learning, most existing deep learning OFE methods still struggle to handle occlusions; in…