Related papers: Video Motion Graphs
We propose an approach for forecasting video of complex human activity involving multiple people. Direct pixel-level prediction is too simple to handle the appearance variability in complex activities. Hence, we develop novel intermediate…
Human motion generation has been widely studied due to its crucial role in areas such as digital humans and humanoid robot control. However, many current motion generation approaches disregard physics constraints, frequently resulting in…
While recent generative video models have achieved remarkable visual realism and are being explored as world models, true physical simulation requires mastering both space and time. Current models can produce visually smooth kinematics, yet…
This paper presents a novel approach to generating the 3D motion of a human interacting with a target object, with a focus on solving the challenge of synthesizing long-range and diverse motions, which could not be fulfilled by existing…
Recent works on dynamic 3D neural field reconstruction assume the input from synchronized multi-view videos whose poses are known. The input constraints are often not satisfied in real-world setups, making the approach impractical. We show…
Interactive humanoid video generation aims to synthesize lifelike visual agents that can engage with humans through continuous and responsive video. Despite recent advances in video synthesis, existing methods often grapple with the…
Complex scenes present significant challenges for predicting human behaviour due to the abundance of interaction information, such as human-human and humanenvironment interactions. These factors complicate the analysis and understanding of…
This paper introduces OmniMotion-X, a versatile multimodal framework for whole-body human motion generation, leveraging an autoregressive diffusion transformer in a unified sequence-to-sequence manner. OmniMotion-X efficiently supports…
Existing learning-based frame interpolation algorithms extract consecutive frames from high-speed natural videos to train the model. Compared to natural videos, cartoon videos are usually in a low frame rate. Besides, the motion between…
Video frame interpolation (VFI) is a fundamental vision task that aims to synthesize several frames between two consecutive original video images. Most algorithms aim to accomplish VFI by using only keyframes, which is an ill-posed problem…
In this paper, we study video synthesis with emphasis on simplifying the generation conditions. Most existing video synthesis models or datasets are designed to address complex motions of a single object, lacking the ability of…
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…
Video interpolation is an important problem in computer vision, which helps overcome the temporal limitation of camera sensors. Existing video interpolation methods usually assume uniform motion between consecutive frames and use linear…
Animation of humanoid characters is essential in various graphics applications, but requires significant time and cost to create realistic animations. We propose an approach to synthesize 4D animated sequences of input static 3D humanoid…
Human-Object Interaction (HOI) detection, which localizes and infers relationships between human and objects, plays an important role in scene understanding. Although two-stage HOI detectors have advantages of high efficiency in training…
We hypothesize dance as a motion that forms a visual rhythm from music, where the visual rhythm can be perceived from an optical flow. If an agent can recognize the relationship between visual rhythm and music, it will be able to dance by…
Video frame interpolation (VFI) serves as a useful tool for many video processing applications. Recently, it has also been applied in the video compression domain for enhancing both conventional video codecs and learning-based compression…
Frame interpolation is an essential video processing technique that adjusts the temporal resolution of an image sequence. While deep learning has brought great improvements to the area of video frame interpolation, techniques that make use…
Accepted in the ICIP 2025 We present a novel transformer-based framework for whole-body grasping that addresses both pose generation and motion infilling, enabling realistic and stable object interactions. Our pipeline comprises three…
The field has made significant progress in synthesizing realistic human motion driven by various modalities. Yet, the need for different methods to animate various body parts according to different control signals limits the scalability of…