Jian Zhang

Associate Professor@Peking University·中国·OpenReview

研究方向

image generation · image restoration · image editing · compressive sensing · deep unfolding network · image compression · computational imaging · image enhancement · super resolution · sparse representation

Jian Zhang

Improved Adversarial Diffusion Compression for Real-World Video Super-Resolution

Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment

GenCompositor: Generative Video Compositing with Diffusion Transformer

CTSR: Controllable Fidelity-Realness Trade-off Distillation for Real-World Image Super Resolution

LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter

Q-Insight: Understanding Image Quality via Visual Reinforcement Learning

FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models

ReCon-GS: Continuum-Preserved Guassian Streaming for Fast and Compact Reconstruction of Dynamic Scenes

SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography

AlignedGen: Aligning Style Across Generated Images

RelayGS: Reconstructing High-Fidelity Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians

Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation