Explanipedia

InfinityHuman: Towards Long-Term Audio-Driven Human Open

Xiaodi Li, Pan Xie, Yi Ren, Qijun Gan, Chen Zhang , et al. · 2025

Audio-driven human animation has attracted wide attention thanks to its practical applications. However, critical challenges remain in generating high-resolution, long-duration videos with consistent appearance and natural hand motions. Ex…

HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation Open

Qijun Gan, Yi Ren, Chen Zhang, Zhenhui Ye, Pan Xie , et al. · 2025

Human motion video generation has advanced significantly, while existing methods still struggle with accurately rendering detailed body parts like hands and faces, especially in long sequences and intricate motions. Current approaches also…

Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering Open

Qijun Gan, Wentong Li, Jinwei Ren, Jianke Zhu · 2024

Reconstructing high-fidelity hand models with intricate textures plays a crucial role in enhancing human-object interaction and advancing real-world applications. Despite the state-of-the-art methods excelling in texture generation and ima…

PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance Open

Qijun Gan, Song Wang, Shengtao Wu, Jing Zhu · 2024

Recently, artificial intelligence techniques for education have been received increasing attentions, while it still remains an open problem to design the effective music instrument instructing systems. Although key presses can be directly …

Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering Open

Qijun Gan, Wentong Li, Jinwei Ren, Jianke Zhu · 2024

Reconstructing high-fidelity hand models with intricate textures plays a crucial role in enhancing human-object interaction and advancing real-world applications. Despite the state-of-the-art methods excelling in texture generation and ima…

FastHuman: Reconstructing High-Quality Clothed Human in Minutes Open

Lixiang Lin, Songyou Peng, Qijun Gan, Jianke Zhu · 2022

We propose an approach for optimizing high-quality clothed human body shapes in minutes, using multi-view posed images. While traditional neural rendering methods struggle to disentangle geometry and appearance using only rendering loss, a…

Qijun Gan YOU? Author Swipe