CompressedVQA-AEV: Full-Reference and No-Reference Quality Assessment Models for Asymmetric Encoded Videos
This work addresses the challenge of assessing quality in asymmetric encoded videos, providing competitive solutions for a specific grand challenge, but the improvements are incremental.
The authors propose full-reference and no-reference video quality assessment models for asymmetric encoded videos, achieving first place in the FR track and fourth place in the NR track of the QoMEX 2026 Grand Challenge.
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.