Zicheng Zhang

Point-cloud-quality-assessment. Collections of papers, databases, and codes targeted at point cloud quality assessment (PCQA), mesh quality assessment (MQA), 3D model quality assessment (3DQA).

Q-SiT. Teaching LMMs for Image Quality Scoring and Interpreting

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

NR-3DQA. Point cloud version for "No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh models".

MM-PCQA. Official repo for 'MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessment' IJCAI2023

GMS-3DQA. Official repo for "GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessment"

MD-VQA. Backup repo for "MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos"

MLLM-QA-Papers-with-Code. Collections of papers and code for employing MLLM for quality assessment tasks.

SJTU-H3D. [TIP 2025] Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluation

CGIQA6K. Offcial repo for 'Subjective and Objective Quality Assessment for in-the-Wild Computer Graphics Images'

NLIEE. This is the code for the paper "A No-reference Evaluation Metric for Low-light Image Enhancement "

VQA_PC. Treating point cloud as moving camera videos: a no-reference quality assessment metric

RR-DHQA. Official repo for "A Reduced-Reference Quality Assessment Metric for Textured Mesh Digital Humans", ICASSP 2024.

DDH-QA. Official repo for 'DDH-QA: A Dynamic Digital Humans Quality Assessment Database'

VP_PCQA. Official repo for "Optimizing Projection-based Point Cloud Quality Assessment with Human Preferred Viewpoints Selection"

DHHQA. Official access to 'Perceptual Quality Assessment for Digital Human Heads'

VLMEvalKit. Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 30+ benchmarks

BVQI. [ICME 2023 Oral, Extended to TIP (UR)] The best zero-shot VQA approach that even outperforms several fully-supervised methods.

LMM-Evaluation-Survey.

Q-Bench. TL, DR: A systematic benchmark for multi-modality LLMs (MLLMs) on low-level vision and visual quality assessment.

CGIQA-1K2. Download links for "Subjective Quality Assessment for Images Generated by Computer Graphics"

Q-Instruct. TL, DR: Low-level visual instruction tuning, with dataset and fine-tuned checkpoints.

CG_GUI. Python