Related papers: Towards Efficient Real-Time Video Motion Transfer …
Event-based video reconstruction has garnered increasing attention due to its advantages, such as high dynamic range and rapid motion capture capabilities. However, current methods often prioritize the extraction of temporal information…
Generating video from various conditions, such as text, image, and audio, enables both spatial and temporal control, leading to high-quality generation results. Videos with dramatic motions often require a higher frame rate to ensure smooth…
Generating videos predicting the future of a given sequence has been an area of active research in recent years. However, an essential problem remains unsolved: most of the methods require large computational cost and memory usage for…
Human motion retargeting aims to transfer the motion of one person in a "driving" video or set of images to another person. Existing efforts leverage a long training video from each target person to train a subject-specific motion transfer…
Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality. Following…
Extensive research has been conducted on assessing grasp stability, a crucial prerequisite for achieving optimal grasping strategies, including the minimum force grasping policy. However, existing works employ basic feature-level fusion…
This paper proposes a novel generative video compression framework that leverages motion pattern priors, derived from subtle dynamics in common scenes (e.g., swaying flowers or a boat drifting on water), rather than relying on video content…
Modern video generative models based on diffusion models can produce very realistic clips, but they are computationally inefficient, often requiring minutes of GPU time for just a few seconds of video. This inefficiency poses a critical…
Generative video modeling has emerged as a compelling tool to zero-shot reason about plausible physical interactions for open-world manipulation. Yet, it remains a challenge to translate such human-led motions into the low-level actions…
Video restoration, which aims to restore clear frames from degraded videos, has numerous important applications. The key to video restoration depends on utilizing inter-frame information. However, existing deep learning methods often rely…
Existing text-to-video methods struggle to transfer motion smoothly from a reference object to a target object with significant differences in appearance or structure between them. To address this challenge, we introduce MotionShot, a…
Video super-resolution (VSR) is the task of restoring high-resolution frames from a sequence of low-resolution inputs. Different from single image super-resolution, VSR can utilize frames' temporal information to reconstruct results with…
This paper addresses fast semantic segmentation on video.Video segmentation often calls for real-time, or even fasterthan real-time, processing. One common recipe for conserving computation arising from feature extraction is to propagate…
Interlacing is a widely used technique, for television broadcast and video recording, to double the perceived frame rate without increasing the bandwidth. But it presents annoying visual artifacts, such as flickering and silhouette…
We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion. Previous work commonly relies on RNN-based models considering shorter forecast horizons reaching a stationary and often implausible…
Several recent works have directly extended the image masked autoencoder (MAE) with random masking into video domain, achieving promising results. However, unlike images, both spatial and temporal information are important for video…
Video generation primarily aims to model authentic and customized motion across frames, making understanding and controlling the motion a crucial topic. Most diffusion-based studies on video motion focus on motion customization with…
Generating videos guided by camera trajectories poses significant challenges in achieving consistency and generalizability, particularly when both camera and object motions are present. Existing approaches often attempt to learn these…
In this work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time. We show that we are able to perform exact and efficient inference on a densely connected…
Real-time video segmentation is a crucial task for many real-world applications such as autonomous driving and robot control. Since state-of-the-art semantic segmentation models are often too heavy for real-time applications despite their…