Related papers: MotionMix: Weakly-Supervised Diffusion for Control…
We present Wan-Move, a simple and scalable framework that brings motion control to video generative models. Existing motion-controllable methods typically suffer from coarse control granularity and limited scalability, leaving their outputs…
Generating realistic motions for digital humans is time-consuming for many graphics applications. Data-driven motion synthesis approaches have seen solid progress in recent years through deep generative models. These results offer…
Diffusion models generate images with an unprecedented level of quality, but how can we freely rearrange image layouts? Recent works generate controllable scenes via learning spatially disentangled latent codes, but these methods do not…
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.…
Recent advancements in diffusion models have shown great promise in producing high-quality video content. However, efficiently training video diffusion models capable of integrating directional guidance and controllable motion intensity…
Recent advances in diffusion models have driven remarkable progress in image generation. However, the generation process remains computationally intensive, and users often need to iteratively refine prompts to achieve the desired results,…
Recent advances in text-to-motion generation using diffusion and autoregressive models have shown promising results. However, these models often suffer from a trade-off between real-time performance, high fidelity, and motion editability.…
The gradual nature of a diffusion process that synthesizes samples in small increments constitutes a key ingredient of Denoising Diffusion Probabilistic Models (DDPM), which have presented unprecedented quality in image synthesis and been…
Distilled video generation models offer fast and efficient synthesis but struggle with motion customization when guided by reference videos, especially under training-free settings. Existing training-free methods, originally designed for…
Diffusion models have opened the path to a wide range of text-based image editing frameworks. However, these typically build on the multi-step nature of the diffusion backwards process, and adapting them to distilled, fast-sampling methods…
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…
Audio-driven simultaneous gesture generation is vital for human-computer communication, AI games, and film production. While previous research has shown promise, there are still limitations. Methods based on VAEs are accompanied by issues…
Generating long-term, coherent, and realistic music-conditioned dance sequences remains a challenging task in human motion synthesis. Existing approaches exhibit critical limitations: motion graph methods rely on fixed template libraries,…
Diffusion models for continuous data gained widespread adoption owing to their high quality generation and control mechanisms. However, controllable diffusion on discrete data faces challenges given that continuous guidance methods do not…
The substantial training cost of diffusion models hinders their deployment. Immiscible Diffusion recently showed that reducing diffusion trajectory mixing in the noise space via linear assignment accelerates training by simplifying…
Despite remarkable achievements in video synthesis, achieving granular control over complex dynamics, such as nuanced movement among multiple interacting objects, still presents a significant hurdle for dynamic world modeling, compounded by…
Latent video diffusion models generate videos by progressively transforming Gaussian noise into realistic samples conditioned on text or visual inputs. However, existing conditioning methods often require additional training and…
In text-to-motion generation, controllability as well as generation quality and speed has become increasingly critical. The controllability challenges include generating a motion of a length that matches the given textual description and…
Image-based motion prediction is one of the essential techniques for robot manipulation. Among the various prediction models, we focus on diffusion models because they have achieved state-of-the-art performance in various applications. In…
Synthesizing realistic human-object interaction motions is a critical problem in VR/AR and human animation. Unlike the commonly studied scenarios involving a single human or hand interacting with one object, we address a more generic…