Related papers: QS-Craft: Learning to Quantize, Scrabble and Craft…
Scenes are continuously undergoing dynamic changes in the real world. However, existing human-scene interaction generation methods typically treat the scene as static, which deviates from reality. Inspired by world models, we introduce…
Text-driven human motion generation is an emerging task in animation and humanoid robot design. Existing algorithms directly generate the full sequence which is computationally expensive and prone to errors as it does not pay special…
Motion generation, the task of synthesizing realistic motion sequences from various conditioning inputs, has become a central problem in computer vision, computer graphics, and robotics, with applications ranging from animation and virtual…
For action recognition learning, 2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame. Recent efforts attempt to capture motion information by establishing…
Recent advances in end-to-end video compression have shown promising results owing to their unified end-to-end learning optimization. However, such generalized frameworks often lack content-specific adaptation, leading to suboptimal…
Scene graph generation is a sophisticated task because there is no specific recognition pattern (e.g., "looking at" and "near" have no conspicuous difference concerning vision, whereas "near" could occur between entities with different…
We tackle the task of diverse 3D human motion prediction, that is, forecasting multiple plausible future 3D poses given a sequence of observed 3D poses. In this context, a popular approach consists of using a Conditional Variational…
Doodling is a useful and common intelligent skill that people can learn and master. In this work, we propose a two-stage learning framework to teach a machine to doodle in a simulated painting environment via Stroke Demonstration and deep…
Sequential visual task usually requires to pay attention to its current interested object conditional on its previous observations. Different from popular soft attention mechanism, we propose a new attention framework by introducing a novel…
Recent advances in video diffusion models have significantly improved character animation techniques. However, current approaches rely on basic structural conditions such as DWPose or SMPL-X to animate character images, limiting their…
Generalist Vision-Language-Action models are currently hindered by the scarcity of robotic data compared to the abundance of human video demonstrations. Existing Latent Action Models attempt to leverage video data but often suffer from…
Automatically generating natural, diverse and rhythmic human dance movements driven by music is vital for virtual reality and film industries. However, generating dance that naturally follows music remains a challenge, as existing methods…
Training a robotic arm to accomplish real-world tasks has been attracting increasing attention in both academia and industry. This work discusses the role of computer vision algorithms in this field. We focus on low-cost arms on which no…
Deep video action recognition models have been highly successful in recent years but require large quantities of manually annotated data, which are expensive and laborious to obtain. In this work, we investigate the generation of synthetic…
Human motion data is inherently rich and complex, containing both semantic content and subtle stylistic features that are challenging to model. We propose a novel method for effective disentanglement of the style and content in human motion…
Synthesizing realistic videos of humans using neural networks has been a popular alternative to the conventional graphics-based rendering pipeline due to its high efficiency. Existing works typically formulate this as an image-to-image…
Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-level tracking driven by acoustic or visual cues, without…
We present a novel framework for animating humans in 3D scenes using 3D Gaussian Splatting (3DGS), a neural scene representation that has recently achieved state-of-the-art photorealistic results for novel-view synthesis but remains…
We present a generative model that learns to synthesize human motion from limited training sequences. Our framework provides conditional generation and blending across multiple temporal resolutions. The model adeptly captures human motion…
We propose a new method for realistic human motion transfer using a generative adversarial network (GAN), which generates a motion video of a target character imitating actions of a source character, while maintaining high authenticity of…