VidGen-1M: A Large-Scale Dataset for Text-to-video Generation
원문 초록
The quality of video-text pairs fundamentally determines the upper bound of text-to-video models. Currently, the datasets used for training these models suffer from significant shortcomings, including low temporal consistency, poor-quality captions, substandard video quality, and imbalanced data distribution. The prevailing video curation process, which depends on image models for tagging and manual rule-based curation, leads to a high computational load and leaves behind unclean data. As a result, there is a lack of appropriate training datasets for text-to-video models. To address this problem, we present VidGen-1M, a superior training dataset for text-to-video models. Produced through a coarse-to-fine curation strategy, this dataset guarantees high-quality videos and detailed captions with excellent temporal consistency. When used to train the video generation model, this dataset has led to experimental results that surpass those obtained with other models.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation
InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPO
LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation
On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices
VPO: Aligning Text-to-Video Generation Models with Prompt Optimization
RecTable: Fast Modeling Tabular Data with Rectified Flow
토론
이 논문과 연결된 포럼 글이 아직 없습니다.