AI Paper Atlas

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

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment

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 changedWhereMeasuredEffect
add multi-scale feature aggregation (MFA) (ablation)Assessor360 · MVAQDSRCC: 0.8514 -> 0.9607Improved
add distortion-aware block (DAB) (ablation)Assessor360 · MVAQDSRCC: 0.8437 -> 0.9607Improved
replace global average pooling with GRU (ablation)Assessor360 · MVAQDSRCC: 0.9393 -> 0.9607Improved
replace temporal pooling with GRU (ablation)Assessor360 · MVAQDSRCC: 0.8942 -> 0.9607Improved
replace LSTM with GRU (ablation)Assessor360 · MVAQDSRCC: 0.9261 -> 0.9607Improved
replace Transformer with GRU (ablation)Assessor360 · MVAQDSRCC: 0.9368 -> 0.9607Improved
use RPS viewport sequences instead of random generation (ablation)Assessor360 · OIQASRCC: 0.9461 -> 0.9802Improved
use RPS instead of ScanGAN360 (ablation)Assessor360 · OIQASRCC: 0.9705 -> 0.9802Improved
use RPS instead of ScanDMM (ablation)Assessor360 · MVAQDSRCC: 0.9558 -> 0.9607Improved
use RPS instead of ERP input (ablation)Assessor360 · MVAQDSRCC: 0.9076 -> 0.9607Improved
start sequences at latitude 60 instead of 0 (ablation)Assessor360 · MVAQDSRCC: 0.9607 -> 0.9106Hurt
shift starting points in longitude only (ablation)Assessor360 · MVAQDSRCC: 0.9607 -> 0.9599No 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy