Tianhe Wu

PhD student, City University of Hong Kong

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

2 papers

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank

#4618 Spotlight · Tianhe Wu, Jian Zou, Jie Liang, Lei Zhang, Kede Ma

We develop a reasoning-induced NR-IQA model via reinforcement learning to rank.

DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution

#4518 · Rongyuan Wu, Lingchen Sun, Zhengqiang ZHANG, Shihao Wang, Tianhe Wu, Qiaosi Yi, Shuai Li, Lei Zhang

DP²O-SR post-trains generative SR models to better match human perceptual preferences, by optimizing over diverse outputs (sampled only via noise) using IQA-based rewards, without requiring human annotations during training.