Picture for Huiyu Duan

Huiyu Duan

Omni$^2$: Unifying Omnidirectional Image Generation and Editing in an Omni Model

Add code
Apr 15, 2025
Viaarxiv icon

FVQ: A Large-Scale Dataset and A LMM-based Method for Face Video Quality Assessment

Add code
Apr 12, 2025
Viaarxiv icon

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

Add code
Apr 11, 2025
Viaarxiv icon

Multi-Dimensional Quality Assessment for Text-to-3D Assets: Dataset and Model

Add code
Feb 24, 2025
Viaarxiv icon

Facial Attractiveness Prediction in Live Streaming: A New Benchmark and Multi-modal Method

Add code
Jan 05, 2025
Figure 1 for Facial Attractiveness Prediction in Live Streaming: A New Benchmark and Multi-modal Method
Figure 2 for Facial Attractiveness Prediction in Live Streaming: A New Benchmark and Multi-modal Method
Figure 3 for Facial Attractiveness Prediction in Live Streaming: A New Benchmark and Multi-modal Method
Figure 4 for Facial Attractiveness Prediction in Live Streaming: A New Benchmark and Multi-modal Method
Viaarxiv icon

HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessment

Add code
Jan 02, 2025
Figure 1 for HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessment
Figure 2 for HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessment
Figure 3 for HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessment
Figure 4 for HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessment
Viaarxiv icon

ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos

Add code
Dec 29, 2024
Figure 1 for ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos
Figure 2 for ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos
Figure 3 for ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos
Figure 4 for ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos
Viaarxiv icon

FineVQ: Fine-Grained User Generated Content Video Quality Assessment

Add code
Dec 26, 2024
Figure 1 for FineVQ: Fine-Grained User Generated Content Video Quality Assessment
Figure 2 for FineVQ: Fine-Grained User Generated Content Video Quality Assessment
Figure 3 for FineVQ: Fine-Grained User Generated Content Video Quality Assessment
Figure 4 for FineVQ: Fine-Grained User Generated Content Video Quality Assessment
Viaarxiv icon

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

Add code
Dec 17, 2024
Viaarxiv icon

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

Add code
Nov 26, 2024
Figure 1 for AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM
Figure 2 for AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM
Figure 3 for AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM
Figure 4 for AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM
Viaarxiv icon