Related papers: DDFlow: Learning Optical Flow with Unlabeled Data …

Diffusion Q-Learning (DQL) has established diffusion policies as a high-performing paradigm for offline reinforcement learning, but its reliance on multi-step denoising for action generation renders both training and inference slow and…

Sampling from pretrained diffusion and flow-matching models typically requires many forward passes to generate diverse and high-fidelity images. Existing distillation methods often rely on multiple auxiliary networks, carefully designed…

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…

Traditional unsupervised optical flow methods are vulnerable to occlusions and motion boundaries due to lack of object-level information. Therefore, we propose UnSAMFlow, an unsupervised flow network that also leverages object information…

Diffusion-based imitation learning improves Behavioral Cloning (BC) on multi-modal decision-making, but comes at the cost of significantly slower inference due to the recursion in the diffusion process. It urges us to design efficient…

Knowledge distillation is an effective approach to transferring knowledge from a teacher neural network to a student target network for satisfying the low-memory and fast running requirements in practice use. Whilst being able to create…

Estimating 3D occupancy and motion at the vehicle's surroundings is essential for autonomous driving, enabling situational awareness in dynamic environments. Existing approaches jointly learn geometry and motion but rely on expensive 3D…

In this paper, we propose a unified method to jointly learn optical flow and stereo matching. Our first intuition is stereo matching can be modeled as a special case of optical flow, and we can leverage 3D geometry behind stereoscopic…

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…

A training pipeline for optical flow CNNs consists of a pretraining stage on a synthetic dataset followed by a fine tuning stage on a target dataset. However, obtaining ground truth flows from a target video requires a tremendous effort.…

Significant progress has been made for estimating optical flow using deep neural networks. Advanced deep models achieve accurate flow estimation often with a considerable computation complexity and time-consuming training processes. In this…

We present an unsupervised optical flow estimation method by proposing an adaptive pyramid sampling in the deep pyramid network. Specifically, in the pyramid downsampling, we propose an Content Aware Pooling (CAP) module, which promotes…

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…

Interpreting the predictions of a black-box deep network can facilitate the reliability of its deployment. In this work, we propose a re-label distillation approach to learn a direct map from the input to the prediction in a…

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…

The estimation of optical flow is an ambiguous task due to the lack of correspondence at occlusions, shadows, reflections, lack of texture and changes in illumination over time. Thus, unsupervised methods face major challenges as they need…

Efficient models for remote sensing object counting are urgently required for applications in scenarios with limited computing resources, such as drones or embedded systems. A straightforward yet powerful technique to achieve this is…

Estimating per-pixel motion between video frames, known as optical flow, is a long-standing problem in video understanding and analysis. Most contemporary optical flow techniques largely focus on addressing the cross-image matching with…

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…

Optical flow estimation is one of the fundamental tasks in low-level computer vision, which describes the pixel-wise displacement and can be used in many other tasks. From the apparent aspect, the optical flow can be viewed as the…