AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

NVS-SQA: Exploring Self-Supervised Quality Representation Learning for Neurally Synthesized Scenes Without References

Qiang Qu, Yiran Shen, Xiaoming Chen, Yuk Ying Chung, Weidong Cai, Tongliang Liu

TPAMI 2025 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning

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 IQA branch to AQB (ablation)NVS-SQA · FieldworkSRCC: 0.7832 -> 0.9111Improved
add VQA branch to AQB (ablation)NVS-SQA · LabSRCC: 0.5519 -> 0.7000Improved
add REP branch to AQB (ablation)NVS-SQA · LLFFSRCC: 0.6218 -> 0.7000Improved
add REP branch to AQB (ablation)NVS-SQA · FieldworkSRCC: 0.8463 -> 0.9111Improved
add VQA branch to AQB (ablation)NVS-SQA · FieldworkSRCC: 0.8297 -> 0.9111Improved
add IQA branch to AQB (ablation)NVS-SQA · LabSRCC: 0.6514 -> 0.7000Improved
use auto-weighting AQB instead of manual weights MBW with all three branches (ablation)NVS-SQA · FieldworkSRCC: 0.8778 -> 0.9111Improved
use auto-weighting AQB instead of manual weights MBW with all three branches (ablation)NVS-SQA · LabSRCC: 0.6429 -> 0.7000Improved
add REP branch to IQA+VQA with manual weights (ablation)NVS-SQA (MBW) · LabSRCC: 0.6874 -> 0.6429Hurt
add VQA branch to IQA alone with manual weights (ablation)NVS-SQA (MBW) · FieldworkSRCC: 0.8556 -> 0.6778Hurt
use NVS-SQA instead of CONTRIQUECONTRIQUE · FieldworkSRCC: 0.689 -> 0.911Improved
use NVS-SQA instead of CONTRIQUE in cross-dataset testCONTRIQUE · LLFF (cross-dataset)SRCC: -0.013 -> 0.671Improved

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