Research map / Image generation / Autoregressive and latent generation
Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment
Tianhe Wu, Shuwei Shi, Haoming Cai, Mingdeng Cao, Jing Xiao, Yinqiang Zheng, Yujiu Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-scale feature aggregation (MFA) (ablation) | Assessor360 · MVAQD | SRCC: 0.8514 -> 0.9607 | Improved |
| add distortion-aware block (DAB) (ablation) | Assessor360 · MVAQD | SRCC: 0.8437 -> 0.9607 | Improved |
| replace global average pooling with GRU (ablation) | Assessor360 · MVAQD | SRCC: 0.9393 -> 0.9607 | Improved |
| replace temporal pooling with GRU (ablation) | Assessor360 · MVAQD | SRCC: 0.8942 -> 0.9607 | Improved |
| replace LSTM with GRU (ablation) | Assessor360 · MVAQD | SRCC: 0.9261 -> 0.9607 | Improved |
| replace Transformer with GRU (ablation) | Assessor360 · MVAQD | SRCC: 0.9368 -> 0.9607 | Improved |
| use RPS viewport sequences instead of random generation (ablation) | Assessor360 · OIQA | SRCC: 0.9461 -> 0.9802 | Improved |
| use RPS instead of ScanGAN360 (ablation) | Assessor360 · OIQA | SRCC: 0.9705 -> 0.9802 | Improved |
| use RPS instead of ScanDMM (ablation) | Assessor360 · MVAQD | SRCC: 0.9558 -> 0.9607 | Improved |
| use RPS instead of ERP input (ablation) | Assessor360 · MVAQD | SRCC: 0.9076 -> 0.9607 | Improved |
| start sequences at latitude 60 instead of 0 (ablation) | Assessor360 · MVAQD | SRCC: 0.9607 -> 0.9106 | Hurt |
| shift starting points in longitude only (ablation) | Assessor360 · MVAQD | SRCC: 0.9607 -> 0.9599 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ScanDMM — ScanDMM: A Deep Markov Model of Scanpath Prediction for 360deg Images (CVPR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment (CVPR 2025 · similarity 0.85)
- Modular Blind Video Quality Assessment (CVPR 2024 · similarity 0.84)
- Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment (ICML 2024 · similarity 0.83)
- Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare (NeurIPS 2024 · similarity 0.83)
- Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered (NeurIPS 2026 · similarity 0.83)
- ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments? (ICLR 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
