Related papers: OptFlow: Fast Optimization-based Scene Flow Estima…

Learning scene flow from a monocular camera still remains a challenging task due to its ill-posedness as well as lack of annotated data. Self-supervised methods demonstrate learning scene flow estimation from unlabeled data, yet their…

In the last few years, convolutional neural networks (CNNs) have demonstrated increasing success at learning many computer vision tasks including dense estimation problems such as optical flow and stereo matching. However, the joint…

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…

A major challenge for video semantic segmentation is the lack of labeled data. In most benchmark datasets, only one frame of a video clip is annotated, which makes most supervised methods fail to utilize information from the rest of the…

Scene flow estimation is an essential ingredient for a variety of real-world applications, especially for autonomous agents, such as self-driving cars and robots. While recent scene flow estimation approaches achieve a reasonable accuracy,…

Event cameras capture brightness changes asynchronously with microsecond resolution, yet existing optical flow methods fail to fully exploit this temporal continuity. Frame-based approaches impose artificial accumulation latency and suffer…

Efficient and accurate motion prediction is crucial for ensuring safety and informed decision-making in autonomous driving, particularly under dynamic real-world conditions that necessitate multi-modal forecasts. We introduce TrajFlow, a…

Most of the top performing action recognition methods use optical flow as a "black box" input. Here we take a deeper look at the combination of flow and action recognition, and investigate why optical flow is helpful, what makes a flow…

Optical flow estimation can be formulated as an end-to-end supervised learning problem, which yields estimates with a superior accuracy-runtime tradeoff compared to alternative methodology. In this paper, we make such networks estimate…

The scarcity of ground-truth labels poses one major challenge in developing optical flow estimation models that are both generalizable and robust. While current methods rely on data augmentation, they have yet to fully exploit the rich…

Dense optical flow estimation plays a key role in many robotic vision tasks. In the past few years, with the advent of deep learning, we have witnessed great progress in optical flow estimation. However, current networks often consist of a…

Tracking motions of humans or objects in the surroundings of the robot is essential to improve safe robot motions and reactions. In this work, we present an approach for scene flow estimation from low-density and noisy point clouds acquired…

Scene flow describes 3D motion in a 3D scene. It can either be modeled as a single task, or it can be reconstructed from the auxiliary tasks of stereo depth and optical flow estimation. While the second method can achieve real-time…

Scene flow enables an understanding of the motion characteristics of the environment in the 3D world. It gains particular significance in the long-range, where object-based perception methods might fail due to sparse observations far away.…

Optical flow techniques are becoming increasingly performant and robust when estimating motion in a scene, but their performance has yet to be proven in the area of facial expression recognition. In this work, a variety of optical flow…

This paper proposes a specialized autonomous driving system that takes into account the unique constraints and characteristics of automotive systems, aiming for innovative advancements in autonomous driving technology. The proposed system…

Semantic occupancy has recently gained significant traction as a prominent 3D scene representation. However, most existing methods rely on large and costly datasets with fine-grained 3D voxel labels for training, which limits their…

Recently, the RGB images and point clouds fusion methods have been proposed to jointly estimate 2D optical flow and 3D scene flow. However, as both conventional RGB cameras and LiDAR sensors adopt a frame-based data acquisition mechanism,…

Vehicle detection and localization in complex traffic scenarios pose significant challenges due to the interference of moving objects. Traditional methods often rely on outlier exclusions or semantic segmentations, which suffer from low…

We propose a novel method for learning convolutional neural image representations without manual supervision. We use motion cues in the form of optical flow, to supervise representations of static images. The obvious approach of training a…