Related papers: ResFlow: Fine-tuning Residual Optical Flow for Eve…

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…

We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived from rigorous RL theory, ReinFlow injects learnable noise…

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…

Modern e-commerce platforms rely heavily on modeling diverse user feedback to provide personalized services. Consequently, multi-task learning has become an integral part of their ranking systems. However, existing multi-task learning…

Optical flow provides information on relative motion that is an important component in many computer vision pipelines. Neural networks provide high accuracy optical flow, yet their complexity is often prohibitive for application at the edge…

High dynamic range (HDR) imaging is a crucial task in computational photography, which captures details across diverse lighting conditions. Traditional HDR fusion methods face limitations in dynamic scenes with extreme exposure differences,…

Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed due to the requirements of hundreds or even thousands of sampling steps. Existing acceleration sampling techniques inevitably sacrifice…

We present Recurrent Vision Transformers (RVTs), a novel backbone for object detection with event cameras. Event cameras provide visual information with sub-millisecond latency at a high-dynamic range and with strong robustness against…

The objective of this work is to improve the accuracy of building demand forecasting. This is a more challenging task than grid level forecasting. For the said purpose, we develop a new technique called recurrent transform learning (RTL).…

Flow matching has emerged as a promising generative approach that addresses the lengthy sampling times associated with state-of-the-art diffusion models and enables a more flexible trajectory design, while maintaining high-quality image…

Optical flow estimation is a well-studied topic for automated driving applications. Many outstanding optical flow estimation methods have been proposed, but they become erroneous when tested in challenging scenarios that are commonly…

Gathering data and identifying events in various traffic situations remains an essential challenge for the systematic evaluation of a perception system's performance. Analyzing large-scale, typically unstructured, multi-modal, time series…

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…

In recent years, consumer-level depth cameras have been adopted for various applications. However, they often produce depth maps at only a moderately high frame rate (approximately 30 frames per second), preventing them from being used for…

Reinforcement Learning (RL) for training Large Language Models is notoriously unstable. While recent studies attribute this to "training inference mismatch stemming" from inconsistent hybrid engines, standard remedies, such as Importance…

Despite significant progress in deep learning-based optical flow methods, accurately estimating large displacements and repetitive patterns remains a challenge. The limitations of local features and similarity search patterns used in these…

Event cameras have the potential to capture continuous motion information over time and space, making them well-suited for optical flow estimation. However, most existing learning-based methods for event-based optical flow adopt frame-based…

Deep learning inference that needs to largely take place on the 'edge' is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications.…

State-of-the-art frame interpolation methods generate intermediate frames by inferring object motions in the image from consecutive key-frames. In the absence of additional information, first-order approximations, i.e. optical flow, must be…

We address the problem of joint optical flow and camera motion estimation in rigid scenes by incorporating geometric constraints into an unsupervised deep learning framework. Unlike existing approaches which rely on brightness constancy and…