← Search

Jiangnan Ye

2 accepted papers

2025

MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement

AAAI 2025technical

Existing works in single-image human reconstruction suffer from weak generalizability due to insufficient training data or 3D inconsistencies for a lack of comprehensive multi-view knowledge. In this paper, we introduce MagicMan, a human-specific multi-view diffusion model to generate high-quality n…

Cited by 8SourcePDFScholar
2024

FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance

ECCV 2024poster

"CLIP has achieved impressive zero-shot performance after pretraining on a large-scale dataset consisting of paired image-text data. Previous works have utilized CLIP by incorporating manually designed visual prompts like colored circles and blur masks into the images to guide the model’s attention,…