MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training
원문 초록
In motion generation, controllability as well as generation quality and speed is becoming more and more important. There are various motion editing tasks, such as in-betweening, upper body editing, and path-following, but existing methods perform motion editing with a data-space diffusion model, which is slow in inference compared to a latent diffusion model. In this paper, we propose MoLA, which provides fast and high-quality motion generation and also can deal with multiple editing tasks in a single framework. For high-quality and fast generation, we employ a variational autoencoder and latent diffusion model, and improve the performance with adversarial training. In addition, we apply a training-free guided generation framework to achieve various editing tasks with motion control inputs. We quantitatively show the effectiveness of adversarial learning in text-to-motion generation, and demonstrate the applicability of our editing framework to multiple editing tasks in the motion domain.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models
Motion Anything: Any to Motion Generation
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss
KETA: Kinematic-Phrases-Enhanced Text-to-Motion Generation via Fine-grained Alignment
Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes
BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.