HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation

• URL: http://arxiv.org/abs/2503.24026v2
• Date: Tue, 01 Apr 2025 03:43:35 GMT
• Title: HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
• Authors: Boyuan Wang, Xiaofeng Wang, Chaojun Ni, Guosheng Zhao, Zhiqin Yang, Zheng Zhu, Muyang Zhang, Yukun Zhou, Xinze Chen, Guan Huang, Lihong Liu, Xingang Wang,
• Abstract summary: We propose a decoupled human video generation framework that first generates diverse poses from text prompts.<n>We present MotionDiT, which is trained to generate structured human-motion poses from text prompts.<n>Our experiments across various Pose-to-Video baselines demonstrate that the poses generated by our method can produce diverse and high-quality human-motion videos.
• Score: 28.007696532331934
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human-motion video generation has been a challenging task, primarily due to the difficulty inherent in learning human body movements. While some approaches have attempted to drive human-centric video generation explicitly through pose control, these methods typically rely on poses derived from existing videos, thereby lacking flexibility. To address this, we propose HumanDreamer, a decoupled human video generation framework that first generates diverse poses from text prompts and then leverages these poses to generate human-motion videos. Specifically, we propose MotionVid, the largest dataset for human-motion pose generation. Based on the dataset, we present MotionDiT, which is trained to generate structured human-motion poses from text prompts. Besides, a novel LAMA loss is introduced, which together contribute to a significant improvement in FID by 62.4%, along with respective enhancements in R-precision for top1, top2, and top3 by 41.8%, 26.3%, and 18.3%, thereby advancing both the Text-to-Pose control accuracy and FID metrics. Our experiments across various Pose-to-Video baselines demonstrate that the poses generated by our method can produce diverse and high-quality human-motion videos. Furthermore, our model can facilitate other downstream tasks, such as pose sequence prediction and 2D-3D motion lifting.

Related papers

• DirectorLLM for Human-Centric Video Generation [46.37441947526771]
  We introduce DirectorLLM, a novel video generation model that employs a large language model (LLM) to orchestrate human poses within videos.<n>Our model outperforms existing ones in generating videos with higher human motion fidelity, improved prompt faithfulness, and enhanced rendered subject naturalness.
  arXiv  Detail & Related papers  (2024-12-19T03:10:26Z)
• Move-in-2D: 2D-Conditioned Human Motion Generation [54.067588636155115]
  We propose Move-in-2D, a novel approach to generate human motion sequences conditioned on a scene image.<n>Our approach accepts both a scene image and text prompt as inputs, producing a motion sequence tailored to the scene.
  arXiv  Detail & Related papers  (2024-12-17T18:58:07Z)
• Fleximo: Towards Flexible Text-to-Human Motion Video Generation [17.579663311741072]
  We introduce a novel task aimed at generating human motion videos solely from reference images and natural language. We propose a new framework called Fleximo, which leverages large-scale pre-trained text-to-3D motion models. To assess the performance of Fleximo, we introduce a new benchmark called MotionBench, which includes 400 videos across 20 identities and 20 motions.
  arXiv  Detail & Related papers  (2024-11-29T04:09:13Z)
• OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation [27.516068877910254]
  We introduce OpenHumanVid, a large-scale and high-quality human-centric video dataset. Our findings yield two critical insights: First, the incorporation of a large-scale, high-quality dataset substantially enhances evaluation metrics for generated human videos. Second, the effective alignment of text with human appearance, human motion, and facial motion is essential for producing high-quality video outputs.
  arXiv  Detail & Related papers  (2024-11-28T07:01:06Z)
• HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation [64.37874983401221]
  We present HumanVid, the first large-scale high-quality dataset tailored for human image animation. For the real-world data, we compile a vast collection of real-world videos from the internet. For the synthetic data, we collected 10K 3D avatar assets and leveraged existing assets of body shapes, skin textures and clothings.
  arXiv  Detail & Related papers  (2024-07-24T17:15:58Z)
• Text2Performer: Text-Driven Human Video Generation [97.3849869893433]
  Text-driven content creation has evolved to be a transformative technique that revolutionizes creativity. Here we study the task of text-driven human video generation, where a video sequence is synthesized from texts describing the appearance and motions of a target performer. In this work, we present Text2Performer to generate vivid human videos with articulated motions from texts.
  arXiv  Detail & Related papers  (2023-04-17T17:59:02Z)
• Human Performance Capture from Monocular Video in the Wild [50.34917313325813]
  We propose a method capable of capturing the dynamic 3D human shape from a monocular video featuring challenging body poses. Our method outperforms state-of-the-art methods on an in-the-wild human video dataset 3DPW.
  arXiv  Detail & Related papers  (2021-11-29T16:32:41Z)
• High-Fidelity Neural Human Motion Transfer from Monocular Video [71.75576402562247]
  Video-based human motion transfer creates video animations of humans following a source motion. We present a new framework which performs high-fidelity and temporally-consistent human motion transfer with natural pose-dependent non-rigid deformations. In the experimental results, we significantly outperform the state-of-the-art in terms of video realism.
  arXiv  Detail & Related papers  (2020-12-20T16:54:38Z)
• Human Motion Transfer from Poses in the Wild [61.6016458288803]
  We tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. It is a video-to-video translation task in which the estimated poses are used to bridge two domains. We introduce a novel pose-to-video translation framework for generating high-quality videos that are temporally coherent even for in-the-wild pose sequences unseen during training.
  arXiv  Detail & Related papers  (2020-04-07T05:59:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.