Related papers: GenOpticalFlow: A Generative Approach to Unsupervi…

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…

Although many deep-learning-based super-resolution approaches have been proposed in recent years, because no ground truth is available in the inference stage, few can quantify the errors and uncertainties of the super-resolved results. For…

Classical computation of optical flow involves generic priors (regularizers) that capture rudimentary statistics of images, but not long-range correlations or semantics. On the other hand, fully supervised methods learn the regularity in…

Diffusion and flow-based generative models have shown strong potential for image restoration. However, image denoising under unknown and varying noise conditions remains challenging, because the learned vector fields may become inconsistent…

3D scene flow estimation aims to estimate point-wise motions between two consecutive frames of point clouds. Superpoints, i.e., points with similar geometric features, are usually employed to capture similar motions of local regions in 3D…

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…

Enhancing the efficiency of high-quality image generation using Diffusion Models (DMs) is a significant challenge due to the iterative nature of the process. Flow Matching (FM) is emerging as a powerful generative modeling paradigm based on…

Optical flow estimation is a basic task in self-driving and robotics systems, which enables to temporally interpret traffic scenes. Autonomous vehicles clearly benefit from the ultra-wide Field of View (FoV) offered by 360{\deg} panoramic…

6D object pose estimation is crucial for robotic perception and precise manipulation. Occlusion and incomplete object visibility are common challenges in this task, but existing pose refinement methods often struggle to handle these issues…

In this paper we propose USegScene, a framework for semantically guided unsupervised learning of depth, optical flow and ego-motion estimation for stereo camera images using convolutional neural networks. Our framework leverages semantic…

The optical flow of natural scenes is a combination of the motion of the observer and the independent motion of objects. Existing algorithms typically focus on either recovering motion and structure under the assumption of a purely static…

Scene flow represents the 3D motion of each point in the scene, which explicitly describes the distance and the direction of each point's movement. Scene flow estimation is used in various applications such as autonomous driving fields,…

Scene flow estimation is a foundational task for many robotic applications, including robust dynamic object detection, automatic labeling, and sensor synchronization. Two types of approaches to the problem have evolved: 1) Supervised and 2)…

Detecting obstacles in railway scenarios is both crucial and challenging due to the wide range of obstacle categories and varying ambient conditions such as weather and light. Given the impossibility of encompassing all obstacle categories…

As the adoption of deep learning techniques in industrial applications grows with increasing speed and scale, successful deployment of deep learning models often hinges on the availability, volume, and quality of annotated data. In this…

Recent works on optical flow estimation use neural networks to predict the flow field that maps positions of one image to positions of the other. These networks consist of a feature extractor, a correlation volume, and finally several…

Super-resolution is an ill-posed problem, since it allows for multiple predictions for a given low-resolution image. This fundamental fact is largely ignored by state-of-the-art deep learning based approaches. These methods instead train a…

We propose Flow Mismatching, an unsupervised anomaly detection method that deliberately avoids reconstruction-based paradigms. Instead, we treat flow matching as geometric dynamics and leverage a key insight: anomalies occur at places where…

Many recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms by encouraging iterative refinements toward a stable flow estimation. However, these RNNs impose large…

Event cameras capture changes of illumination in the observed scene rather than accumulating light to create images. Thus, they allow for applications under high-speed motion and complex lighting conditions, where traditional framebased…