OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation

• URL: http://arxiv.org/abs/2412.00115v3
• Date: Sat, 04 Jan 2025 06:16:56 GMT
• Title: OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
• Authors: Hui Li, Mingwang Xu, Yun Zhan, Shan Mu, Jiaye Li, Kaihui Cheng, Yuxuan Chen, Tan Chen, Mao Ye, Jingdong Wang, Siyu Zhu,
• Abstract summary: 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.
• Score: 27.516068877910254
• License:
• Abstract: Recent advancements in visual generation technologies have markedly increased the scale and availability of video datasets, which are crucial for training effective video generation models. However, a significant lack of high-quality, human-centric video datasets presents a challenge to progress in this field. To bridge this gap, we introduce OpenHumanVid, a large-scale and high-quality human-centric video dataset characterized by precise and detailed captions that encompass both human appearance and motion states, along with supplementary human motion conditions, including skeleton sequences and speech audio. To validate the efficacy of this dataset and the associated training strategies, we propose an extension of existing classical diffusion transformer architectures and conduct further pretraining of our models on the proposed 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 while preserving performance in general video generation tasks. Second, the effective alignment of text with human appearance, human motion, and facial motion is essential for producing high-quality video outputs. Based on these insights and corresponding methodologies, the straightforward extended network trained on the proposed dataset demonstrates an obvious improvement in the generation of human-centric videos. Project page https://fudan-generative-vision.github.io/OpenHumanVid

Related papers

• VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation [79.00294932026266]
  VidMan is a novel framework that employs a two-stage training mechanism to enhance stability and improve data utilization efficiency. Our framework outperforms state-of-the-art baseline model GR-1 on the CALVIN benchmark, achieving a 11.7% relative improvement, and demonstrates over 9% precision gains on the OXE small-scale dataset.
  arXiv  Detail & Related papers  (2024-11-14T03:13:26Z)
• FaceVid-1K: A Large-Scale High-Quality Multiracial Human Face Video Dataset [15.917564646478628]
  We create a high-quality multiracial face collection named textbfFaceVid-1K. We conduct experiments with several well-established video generation models, including text-to-video, image-to-video, and unconditional video generation. We obtain the corresponding performance benchmarks and compared them with those trained on public datasets to demonstrate the superiority of our dataset.
  arXiv  Detail & Related papers  (2024-09-23T07:27:02Z)
• 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)
• A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights [8.192172339127657]
  Human video generation aims to synthesize 2D human body video sequences with generative models given control conditions such as text, audio, and pose. Recent advancements in generative models have laid a solid foundation for the growing interest in this area. Despite the significant progress, the task of human video generation remains challenging due to the consistency of characters, the complexity of human motion, and difficulties in their relationship with the environment.
  arXiv  Detail & Related papers  (2024-07-11T12:09:05Z)
• Data Augmentation in Human-Centric Vision [54.97327269866757]
  This survey presents a comprehensive analysis of data augmentation techniques in human-centric vision tasks. It delves into a wide range of research areas including person ReID, human parsing, human pose estimation, and pedestrian detection. Our work categorizes data augmentation methods into two main types: data generation and data perturbation.
  arXiv  Detail & Related papers  (2024-03-13T16:05:18Z)
• Learning Human Action Recognition Representations Without Real Humans [66.61527869763819]
  We present a benchmark that leverages real-world videos with humans removed and synthetic data containing virtual humans to pre-train a model. We then evaluate the transferability of the representation learned on this data to a diverse set of downstream action recognition benchmarks. Our approach outperforms previous baselines by up to 5%.
  arXiv  Detail & Related papers  (2023-11-10T18:38:14Z)
• Probabilistic Adaptation of Text-to-Video Models [181.84311524681536]
  Video Adapter is capable of incorporating the broad knowledge and preserving the high fidelity of a large pretrained video model in a task-specific small video model. Video Adapter is able to generate high-quality yet specialized videos on a variety of tasks such as animation, egocentric modeling, and modeling of simulated and real-world robotics data.
  arXiv  Detail & Related papers  (2023-06-02T19:00:17Z)
• StyleGAN-Human: A Data-Centric Odyssey of Human Generation [96.7080874757475]
  This work takes a data-centric perspective and investigates multiple critical aspects in "data engineering" We collect and annotate a large-scale human image dataset with over 230K samples capturing diverse poses and textures. We rigorously investigate three essential factors in data engineering for StyleGAN-based human generation, namely data size, data distribution, and data alignment.
  arXiv  Detail & Related papers  (2022-04-25T17:55:08Z)
• Creating a Large-scale Synthetic Dataset for Human Activity Recognition [0.8250374560598496]
  We use 3D rendering tools to generate a synthetic dataset of videos, and show that a classifier trained on these videos can generalise to real videos. We fine tune a pre-trained I3D model on our videos, and find that the model is able to achieve a high accuracy of 73% on the HMDB51 dataset over three classes.
  arXiv  Detail & Related papers  (2020-07-21T22:20:21Z)

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.