OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
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
Code (0)
등록된 구현이 없습니다.
Tasks
Video GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Data Quality Measures and Efficient Evaluation Algorithms for Large-Scale High-Dimensional Data
Machine learning has been proven to be effective in various application areas, such as object and speech recognition on mobile systems. Since a critical key to machine learning success is the availability of large traini…
BIG-bench Machine Learningspeech-recognitionSpeech RecognitionOpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing
The quality and diversity of instruction-based image editing datasets are continuously increasing, yet large-scale, high-quality datasets for instruction-based video editing remain scarce. To address this gap, we introdu…
Image EditingSmolKalam: Ensemble Quality-Filtered Translation at Scale for High Quality Arabic Post-Training Data
Although the community has tackled the acquisition of high-quality Arabic pretraining data, we still lack large-scale, multi-turn Arabic datasets that include reasoning and tool calling. Naive translation can work at the…
Scalable Vision Language Model Training via High Quality Data Curation
In this paper, we introduce SAIL-VL (ScAlable Vision Language Model TraIning via High QuaLity Data Curation), an open-source vision language model (VLM) of state-of-the-art (SOTA) performance with 2B parameters. We intro…
Instruction FollowingLanguage ModelingLanguage ModellingRemoving Noise, not Finding Gold: Quality Filtering for Large-Scale Pretraining
Large-scale models are pretrained on massive web-crawled datasets containing documents of mixed quality, making data filtering essential. A popular method is Classifier-based Quality Filtering (CQF), which trains a binar…