Guangtao Zhai

28

Papers

280

Total Citations

Papers (28)

Towards Open-ended Visual Quality Comparison

A-Bench: Are LMMs Masters at Evaluating AI-generated Images?

FineVQ: Fine-Grained User Generated Content Video Quality Assessment

AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM

OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?

Low-Light Image Enhancement via Generative Perceptual Priors

Free-VSC: Free Semantics from Visual Foundation Models for Unsupervised Video Semantic Compression

LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs

Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing

4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video

TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning

Towards All-in-One Medical Image Re-Identification

Medical Manifestation-Aware De-Identification

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration

Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Heads

Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes

FPEM: Face Prior Enhanced Facial Attractiveness Prediction for Live Videos with Face Retouching

Textured Mesh Saliency: Bridging Geometry and Texture for Human Perception in 3D Graphics

Image Quality Assessment: From Human to Machine Preference

Information Density Principle for MLLM Benchmarks

Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs

VRVVC: Variable-Rate NeRF-Based Volumetric Video Compression

Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content

Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels

Semantic versus Identity: A Divide-and-Conquer Approach towards Adjustable Medical Image De-Identification

Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generation

Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models

Shadow Generation Using Diffusion Model with Geometry Prior