针对不对称编码视频，提出双模型质量评估系统。
CompressedVQA-AEV: Full-Reference and No-Reference Quality Assessment Models for Asymmetric Encoded Videos
- 用Swin-B提取参考与失真视频的多阶段相似性统计
- 无参考模型在未见数据上达第四名，性能领先
- 适合视频编解码器评测与质量监控场景
本报告介绍了我们在 QoMEX 2026 视频质量评估挑战赛中针对不对称编码视频的解决方案，包含全参考（FR）模型 CompressedVQA-AEV-FR 和无参考（NR）模型 CompressedVQA-AEV-NR。FR 方法采用 Swin-B 主干网络，提取参考视频与失真视频间的多阶段相似性统计信息以预测质量。在无参考设置中，模型结合 SigLIP2 与 Swin-B 的帧级编码器，经时间平均池化与跨折叠集成，实现无需参考数据的感知质量估计。CompressedVQA-AEV-FR 在 FR 赛道排名第一，CompressedVQA-AEV-NR 在 NR 赛道位列第四，验证了所提方法的有效性。代码已开源：https://github.com/sunwei925/CompressedVQA-AEV。
原文摘要 · Abstract (English)
This report presents our solutions to the QoMEX 2026 Grand Challenge on Video Quality Assessment for Asymmetric Encoded Videos, comprising a full-reference (FR) model, CompressedVQA-AEV-FR, and a no-reference (NR) model, CompressedVQA-AEV-NR. The FR approach leverages a Swin-B backbone to extract multi-stage similarity statistics between reference and distorted videos for quality prediction. For the NR setting, our model employs complementary frame-level encoders based on SigLIP2 and Swin-B, followed by temporal mean pooling and cross-fold ensembling to estimate perceptual quality without reference data. Our CompressedVQA-AEV-FR achieves first place in the FR track of QoMEX 2026 Grand Challenge, while CompressedVQA-AEV-NR secures fourth place in the NR track, demonstrating the effectiveness of our proposed models. The code is available at https://github.com/sunwei925/CompressedVQA-AEV.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。