R4-CGQA: Retrieval-based Vision Language Models for Computer Graphics Image Quality Assessment

• URL: http://arxiv.org/abs/2603.10578v1
• Date: Wed, 11 Mar 2026 09:28:49 GMT
• Title: R4-CGQA: Retrieval-based Vision Language Models for Computer Graphics Image Quality Assessment
• Abstract summary: We identify six key dimensions of CG quality from the user perspective and construct a dataset of 3500 CG images with corresponding quality descriptions.<n>Each description covers CG style, content, and perceived quality along the selected dimensions.<n>We propose a two-stream retrieval framework that effectively enhances the CG quality assessment capabilities of Vision Language Models.
• Score: 54.214070637335205
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Immersive Computer Graphics (CGs) rendering has become ubiquitous in modern daily life. However, comprehensively evaluating CG quality remains challenging for two reasons: First, existing CG datasets lack systematic descriptions of rendering quality; and second existing CG quality assessment methods cannot provide reasonable text-based explanations. To address these issues, we first identify six key perceptual dimensions of CG quality from the user perspective and construct a dataset of 3500 CG images with corresponding quality descriptions. Each description covers CG style, content, and perceived quality along the selected dimensions. Furthermore, we use a subset of the dataset to build several question-answer benchmarks based on the descriptions in order to evaluate the responses of existing Vision Language Models (VLMs). We find that current VLMs are not sufficiently accurate in judging fine-grained CG quality, but that descriptions of visually similar images can significantly improve a VLM's understanding of a given CG image. Motivated by this observation, we adopt retrieval-augmented generation and propose a two-stream retrieval framework that effectively enhances the CG quality assessment capabilities of VLMs. Experiments on several representative VLMs demonstrate that our method substantially improves their performance on CG quality assessment.

Related papers

• SpatialQ: Understanding 3D Gaussian Splatting Scene Quality via Visual-based MLLM [33.48299658365364]
  A multimodal quality assessment framework is developed for 3DGS scene understanding.<n>A 3D-aware quality representation learning framework is introduced by augmenting a VGGT-based encoder with a dedicated quality head.<n>A grounded multimodal reasoning mechanism is constructed by jointly feeding original images, depth maps, point cloud renderings, and camera parameters into a Qwen-based MLLM.
  arXiv  Detail & Related papers  (2026-07-29T08:14:40Z)
• Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric [76.66966098297986]
  We present 3DGS-QA, the first subjective quality assessment dataset for 3DGS.<n>It comprises 225 degraded reconstructions across 15 object types, enabling a controlled investigation of common distortion factors.<n>Our model extracts spatial and photometric cues from the Gaussian representation to estimate perceived quality in a structure-aware manner.
  arXiv  Detail & Related papers  (2025-11-11T09:34:20Z)
• ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images [27.448161376085658]
  In this study, we establish the first large-scale Visual Distortion Assessment Instruction dataset for images, termed ViDA-UGC.<n>This dataset is constructed through a distortion-oriented pipeline, which involves human subject annotation and a Chain-of-Thought framework.<n>We select 476 images with corresponding 6,149 question answer pairs from ViDA-UGC and invite a professional team to ensure the accuracy and quality of GPT-generated information.<n> Experimental results demonstrate the effectiveness of the ViDA-UGC and CoT framework for consistently enhancing various image quality analysis abilities.
  arXiv  Detail & Related papers  (2025-08-18T04:02:58Z)
• No-Reference Point Cloud Quality Assessment via Graph Convolutional Network [89.12589881881082]
  Three-dimensional (3D) point cloud, as an emerging visual media format, is increasingly favored by consumers. Point clouds inevitably suffer from quality degradation and information loss through multimedia communication systems. We propose a novel no-reference PCQA method by using a graph convolutional network (GCN) to characterize the mutual dependencies of multi-view 2D projected image contents.
  arXiv  Detail & Related papers  (2024-11-12T11:39:05Z)
• VQA$^2$: Visual Question Answering for Video Quality Assessment [76.81110038738699]
  Video Quality Assessment (VQA) is a classic field in low-level visual perception.<n>Recent studies in the image domain have demonstrated that Visual Question Answering (VQA) can enhance markedly low-level visual quality evaluation.<n>We introduce the VQA2 Instruction dataset - the first visual question answering instruction dataset that focuses on video quality assessment.<n>The VQA2 series models interleave visual and motion tokens to enhance the perception of spatial-temporal quality details in videos.
  arXiv  Detail & Related papers  (2024-11-06T09:39:52Z)
• Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Model [56.03592388332793]
  We investigate the AIGC-VQA problem, considering both subjective and objective quality assessment perspectives.<n>For the subjective perspective, we construct the Large-scale Generated Video Quality assessment (LGVQ) dataset, consisting of 2,808 AIGC videos.<n>We evaluate the perceptual quality of AIGC videos from three critical dimensions: spatial quality, temporal quality, and text-video alignment.<n>We propose the Unify Generated Video Quality assessment (UGVQ) model, designed to accurately evaluate the multi-dimensional quality of AIGC videos.
  arXiv  Detail & Related papers  (2024-07-31T07:54:26Z)
• Q-Ground: Image Quality Grounding with Large Multi-modality Models [61.72022069880346]
  We introduce Q-Ground, the first framework aimed at tackling fine-scale visual quality grounding. Q-Ground combines large multi-modality models with detailed visual quality analysis. Central to our contribution is the introduction of the QGround-100K dataset.
  arXiv  Detail & Related papers  (2024-07-24T06:42:46Z)
• A Deep Learning based No-reference Quality Assessment Model for UGC Videos [44.00578772367465]
  Previous video quality assessment (VQA) studies either use the image recognition model or the image quality assessment (IQA) models to extract frame-level features of videos for quality regression. We propose a very simple but effective VQA model, which trains an end-to-end spatial feature extraction network to learn the quality-aware spatial feature representation from raw pixels of the video frames. With the better quality-aware features, we only use the simple multilayer perception layer (MLP) network to regress them into the chunk-level quality scores, and then the temporal average pooling strategy is adopted to obtain the video
  arXiv  Detail & Related papers  (2022-04-29T12:45:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.