(2025-09-15) The inference code of A-FINE is intergrated into the excellent PyIQA codeframe. Please find the detailed usage here. (2025-04-14) We release the DiffIQA dataset. (2025-04-14) We release ...

Don't just texture one mesh at a time! StableGen is designed to apply textures to all mesh objects in your scene simultaneously from your defined camera viewpoints. Alternatively, you can choose to ...

Abstract: Recently, neural networks have become the dominant approach to low-light image enhancement (LLIE), with at least one-third of them adopting a Retinex-related architecture. However, through ...

Google Deepmind has updated Veo 3.1 with new features for generating video from reference images. The update enables more dynamic and expressive videos, even with simple text prompts, according to ...

Images lose quality in multiple ways. Some lose their resolution and gradually degrade with each share. Some lose clarity, some go out of style through over-editing, and physical photos may lose shape ...

Abstract: In the field of no-reference image quality assessment (NR-IQA), the visual masking effect has long been a challenging issue. Although existing methods attempt to alleviate the interference ...