Built independently by an author, for readers. Read the story and support ChapterPal

keyword

face generation

Face generation is a computer vision and artificial intelligence process that creates realistic synthetic visual representations of human faces, ranging from static two-dimensional images and three-dimensional models to dynamic video sequences. Powered by deep generative frameworks such as generative adversarial networks, variational autoencoders, and diffusion models, the technology can synthesize entirely novel facial identities or reconstruct existing ones with customized visual characteristics. These systems can operate unconditionally or be directed by multimodal inputs, including natural language descriptions, audio signals, structural landmarks, or reference images, enabling fine-grained control over attributes such as facial expressions, gaze, head pose, age, lighting, and motion dynamics. Face generation is widely applied in digital entertainment, virtual reality avatars, visual effects, telepresence, and the creation of synthetic training data for biometric systems.

1 item

CelebV-Text: A Large-Scale Facial Text-Video Dataset

CelebV-Text: A Large-Scale Facial Text-Video Dataset

Jianhui Yu, Hao Zhu, Liming Jiang, Chen Change Loy, Weidong Cai, Wayne Wu

Why you should read this

Presents a large-scale dataset of 70,000 in-the-wild facial video clips paired with 1.4 million detailed static and dynamic text descriptions to advance and standardize face-centric text-to-video generation.

Text-driven generation models are flourishing in video generation and editing. However, face-centric text-to-video generation remains a challenge due to the lack of a suitable dataset containing high-quality videos and highly relevant texts. This paper presents CelebV-Text, a large-scale, diverse, and high-quality dataset of facial text-video pairs, to facilitate research on facial text-to-video generation tasks. CelebV-Text comprises 70,000 in-the-wild face video clips with diverse visual content, each paired with 20 texts generated using the proposed semi-automatic text generation strategy. The provided texts are of high quality, describing both static and dynamic attributes precisely. The superiority of CelebV-Text over other datasets is demonstrated via comprehensive statistical analysis of the videos, texts, and text-video relevance. The effectiveness and potential of CelebV-Text are further shown through extensive self-evaluation. A benchmark is constructed with representative methods to standardize the evaluation of the facial text-to-video generation task. All data and models are publicly available^1.

Added

2026-09-26