AIWalker
AIWalker
Mar 13, 2026 · Artificial Intelligence

Towards AI That Truly Understands Art: Introducing the ArtiMuse Aesthetic Understanding Model

ArtiMuse, a new image aesthetic model unveiled at CVPR 2026 by Shanghai AI Lab and the China Academy of Art, combines a massive 10K fine‑grained dataset, a Token‑As‑Score scoring scheme, and unified textual‑and‑numeric feedback to deliver culturally aware, expert‑level art analysis and robust quantitative ratings.

AI aestheticsToken-As-Scoreart analysis
0 likes · 7 min read
Towards AI That Truly Understands Art: Introducing the ArtiMuse Aesthetic Understanding Model
AIWalker
AIWalker
Mar 12, 2026 · Artificial Intelligence

BeautyGRPO: RL‑Driven Realistic Portrait Retouching Ends Over‑Beautification (CVPR 2026)

The paper introduces BeautyGRPO, a reinforcement‑learning framework that combines a fine‑grained preference dataset (FRPref‑10K) with Dynamic Path Guidance to balance aesthetic enhancement and high‑fidelity preservation in portrait retouching, achieving superior metrics and user preference over existing SFT and RL models.

AI aestheticsCVPR 2026dynamic path guidance
0 likes · 11 min read
BeautyGRPO: RL‑Driven Realistic Portrait Retouching Ends Over‑Beautification (CVPR 2026)