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
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 IQA branch to AQB (ablation) | NVS-SQA · Fieldwork | SRCC: 0.7832 -> 0.9111 | Improved |
| add VQA branch to AQB (ablation) | NVS-SQA · Lab | SRCC: 0.5519 -> 0.7000 | Improved |
| add REP branch to AQB (ablation) | NVS-SQA · LLFF | SRCC: 0.6218 -> 0.7000 | Improved |
| add REP branch to AQB (ablation) | NVS-SQA · Fieldwork | SRCC: 0.8463 -> 0.9111 | Improved |
| add VQA branch to AQB (ablation) | NVS-SQA · Fieldwork | SRCC: 0.8297 -> 0.9111 | Improved |
| add IQA branch to AQB (ablation) | NVS-SQA · Lab | SRCC: 0.6514 -> 0.7000 | Improved |
| use auto-weighting AQB instead of manual weights MBW with all three branches (ablation) | NVS-SQA · Fieldwork | SRCC: 0.8778 -> 0.9111 | Improved |
| use auto-weighting AQB instead of manual weights MBW with all three branches (ablation) | NVS-SQA · Lab | SRCC: 0.6429 -> 0.7000 | Improved |
| add REP branch to IQA+VQA with manual weights (ablation) | NVS-SQA (MBW) · Lab | SRCC: 0.6874 -> 0.6429 | Hurt |
| add VQA branch to IQA alone with manual weights (ablation) | NVS-SQA (MBW) · Fieldwork | SRCC: 0.8556 -> 0.6778 | Hurt |
| use NVS-SQA instead of CONTRIQUE | CONTRIQUE · Fieldwork | SRCC: 0.689 -> 0.911 | Improved |
| use NVS-SQA instead of CONTRIQUE in cross-dataset test | CONTRIQUE · LLFF (cross-dataset) | SRCC: -0.013 -> 0.671 | Improved |
Closest papers by meaning
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.87)
- LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias (ICLR 2025 · similarity 0.87)
- Novel View Synthesis with View-Dependent Effects from a Single Image (CVPR 2024 · similarity 0.86)
- UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis (NeurIPS 2025 · similarity 0.86)
- Enhancing Close-up Novel View Synthesis via Pseudo-labeling (AAAI 2025 · similarity 0.86)
- Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion (NeurIPS 2025 · similarity 0.85)
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.
