zhang0jhon

AttentionOCR. Scene text recognition

diffusion-4k. [CVPR 2025] Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models

LogSAD. [CVPR 2025] Towards Training-free Anomaly Detection with Vision and Language Foundation Models

SENSE. [ICML 2026] What Makes Synthetic Data Effective in Image Segmentation

SGA.

kinfu. Makefile

otamatch. Python