Related papers: GyroFlow+: Gyroscope-Guided Unsupervised Deep Homo…

Multi-frame methods improve monocular depth estimation over single-frame approaches by aggregating spatial-temporal information via feature matching. However, the spatial-temporal feature leads to accuracy degradation in dynamic scenes. To…

Modern cameras have limited dynamic ranges and often produce images with saturated or dark regions using a single exposure. Although the problem could be addressed by taking multiple images with different exposures, exposure fusion methods…

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…

Optical flow computation with frame-based cameras provides high accuracy but the speed is limited either by the model size of the algorithm or by the frame rate of the camera. This makes it inadequate for high-speed applications. Event…

Existing work on scene flow estimation focuses on autonomous driving and mobile robotics, while automated solutions are lacking for motion in nature, such as that exhibited by debris flows. We propose DEFLOW, a model for 3D motion…

Optical flow is the motion of a pixel between at least two consecutive video frames and can be estimated through an end-to-end trainable convolutional neural network. To this end, large training datasets are required to improve the accuracy…

Nighttime image dehazing remains a challenging low-level vision problem due to the joint presence of haze, glow, non-uniform illumination, color distortion, and sensor noise, which often invalidate assumptions commonly used in daytime…

Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take…

Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…

Discriminative correlation filters (DCF) with deep convolutional features have achieved favorable performance in recent tracking benchmarks. However, most of existing DCF trackers only consider appearance features of current frame, and…

Optical flow has made great progress in clean scenes, while suffers degradation under adverse weather due to the violation of the brightness constancy and gradient continuity assumptions of optical flow. Typically, existing methods mainly…

Understanding and predicting object motion from egocentric video is fundamental to embodied perception and interaction. However, generating physically consistent 6DoF trajectories remains challenging due to occlusions, fast motion, and the…

Trajectory prediction is a fundamental problem and challenge for autonomous vehicles. Early works mainly focused on designing complicated architectures for deep-learning-based prediction models in normal-illumination environments, which…

We present DeepSurfels, a novel hybrid scene representation for geometry and appearance information. DeepSurfels combines explicit and neural building blocks to jointly encode geometry and appearance information. In contrast to established…

In this paper, we propose an algorithm to interpolate between a pair of images of a dynamic scene. While in the past years significant progress in frame interpolation has been made, current approaches are not able to handle images with…

We introduce a novel training strategy for stereo matching and optical flow estimation that utilizes image-to-image translation between synthetic and real image domains. Our approach enables the training of models that excel in real image…

Infrared and visible image fusion has emerged as a prominent research area in computer vision. However, little attention has been paid to the fusion task in complex scenes, leading to sub-optimal results under interference. To fill this…

Unsupervised optical flow estimation is especially hard near occlusions and motion boundaries and in low-texture regions. We show that additional information such as semantics and domain knowledge can help better constrain this problem. We…

Among the existing modalities for 3D action recognition, 3D flow has been poorly examined, although conveying rich motion information cues for human actions. Presumably, its susceptibility to noise renders it intractable, thus challenging…

Monocular scene flow estimation aims to recover dense 3D motion from image sequences, yet most existing methods are limited to two-frame inputs, restricting temporal modeling and robustness to occlusions. We propose RAFT-MSF++, a…