Shape Conditioned Human Motion Generation with Diffusion Model
원문 초록
Human motion synthesis is an important task in computer graphics and computer vision. While focusing on various conditioning signals such as text, action class, or audio to guide the generation process, most existing methods utilize skeleton-based pose representation, requiring additional skinning to produce renderable meshes. Given that human motion is a complex interplay of bones, joints, and muscles, considering solely the skeleton for generation may neglect their inherent interdependency, which can limit the variability and precision of the generated results. To address this issue, we propose a Shape-conditioned Motion Diffusion model (SMD), which enables the generation of motion sequences directly in mesh format, conditioned on a specified target mesh. In SMD, the input meshes are transformed into spectral coefficients using graph Laplacian, to efficiently represent meshes. Subsequently, we propose a Spectral-Temporal Autoencoder (STAE) to leverage cross-temporal dependencies within the spectral domain. Extensive experimental evaluations show that SMD not only produces vivid and realistic motions but also achieves competitive performance in text-to-motion and action-to-motion tasks when compared to state-of-the-art methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesis
Motion-R1: Chain-of-Thought Reasoning and Reinforcement Learning for Human Motion Generation
UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes
Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion
Text-driven Motion Generation: Overview, Challenges and Directions
Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis
토론
이 논문과 연결된 포럼 글이 아직 없습니다.