Related papers: Controllable Motion Synthesis and Reconstruction w…
The emergence of text-driven motion synthesis technique provides animators with great potential to create efficiently. However, in most cases, textual expressions only contain general and qualitative motion descriptions, while lack fine…
Diffusion Policy (DP) has attracted significant attention as an effective method for policy representation due to its capacity to model multi-distribution dynamics. However, current DPs are often based on a single visual modality (e.g., RGB…
Current approaches for 3D human motion synthesis generate high quality animations of digital humans performing a wide variety of actions and gestures. However, a notable technological gap exists in addressing the complex dynamics of multi…
As Diffusion Models have shown promising performance, a lot of efforts have been made to improve the controllability of Diffusion Models. However, how to train Diffusion Models to have the disentangled latent spaces and how to naturally…
Legged locomotion demands controllers that are both robust and adaptable, while remaining compatible with task and safety considerations. However, model-free reinforcement learning (RL) methods often yield a fixed policy that can be…
Self-supervised learning has garnered increasing attention in time series analysis for benefiting various downstream tasks and reducing reliance on labeled data. Despite its effectiveness, existing methods often struggle to comprehensively…
The scale and quality of a dataset significantly impact the performance of deep models. However, acquiring large-scale annotated datasets is both a costly and time-consuming endeavor. To address this challenge, dataset expansion…
Diffusion models have become a popular choice for human motion synthesis due to their powerful generative capabilities. However, their high computational complexity and large sampling steps pose challenges for real-time applications.…
Lightweight, controllable, and physically plausible human motion synthesis is crucial for animation, virtual reality, robotics, and human-computer interaction applications. Existing methods often compromise between computational efficiency,…
In this study, we introduce a learning-based method for generating high-quality human motion sequences from text descriptions (e.g., ``A person walks forward"). Existing techniques struggle with motion diversity and smooth transitions in…
Music-driven group choreography poses a considerable challenge but holds significant potential for a wide range of industrial applications. The ability to generate synchronized and visually appealing group dance motions that are aligned…
Acquiring aligned visuo-tactile datasets is slow and costly, requiring specialised hardware and large-scale data collection. Synthetic generation is promising, but prior methods are typically single-modality, limiting cross-modal learning.…
Diffusion models, as a type of generative model, have achieved impressive results in generating images and videos conditioned on textual conditions. However, the generation process of diffusion models involves denoising dozens of steps to…
Seismic data frequently exhibits missing traces, substantially affecting subsequent seismic processing and interpretation. Deep learning-based approaches have demonstrated significant advancements in reconstructing irregularly missing…
Diffusion models are renowned for their generative capabilities, yet their pretraining processes exhibit distinct phases of learning speed that have been entirely overlooked in prior post-training acceleration efforts in the community. In…
Diffusion strategies have advanced visual motor control by progressively denoising high-dimensional action sequences, providing a promising method for robot manipulation. However, as task complexity increases, the success rate of existing…
Incorporating physics in human motion capture to avoid artifacts like floating, foot sliding, and ground penetration is a promising direction. Existing solutions always adopt kinematic results as reference motions, and the physics is…
Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge,…
Inverse protein folding generates valid amino acid sequences that can fold into a desired protein structure, with recent deep-learning advances showing strong potential and competitive performance. However, challenges remain, such as…
We propose DemoDiffusion, a simple method for enabling robots to perform manipulation tasks by imitating a single human demonstration, without requiring task-specific training or paired human-robot data. Our approach is based on two…