Research map / 3D vision / 3D generation
CrossScore: A Multi-View Approach to Image Evaluation and Scoring
Zirui Wang, Wenjing Bian, Victor Adrian Prisacariu
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 |
|---|---|---|---|
| provide real multi-view reference images to the cross-reference module (ablation) | CrossScore · MFR scenes | correlation with SSIM: 0.68 -> 0.83 | Improved |
| enable reference images (versus zeroed references) (ablation) | CrossScore · MFR scenes | average predicted score: 0.81 -> 0.65 (SSIM 0.57) | Improved |
| use CrossScore instead of no-reference metrics on MFR | image quality assessment · MFR | correlation with SSIM: -0.30 (NIQE) -> 0.83 | Improved |
| use CrossScore to rank few-shot NeRFs | IBRNet vs PixelNeRF · MFR | ranking agreement with SSIM and PSNR: 0.40 -> 0.71 | Improved |
| evaluate novel trajectories with CrossScore instead of SSIM on held-out views | Gaussian Splatting scenes · MFR scenes | ranking Spearman correlation: 0.85 | Improved |
| apply to fish-eye style query images | CrossScore · limitation case | prediction accuracy | Hurt |
Later papers that compared with this method
2 later accepted papers report CrossScore as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection (ECCV 2026 · better on 3 of 3 shared results)
- Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructions (ICCV 2025 · better on 11 of 14 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
- Towards Open-ended Visual Quality Comparison (ECCV 2024 · similarity 0.87)
- Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare (NeurIPS 2024 · similarity 0.85)
- Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered (NeurIPS 2026 · similarity 0.84)
- FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance (NeurIPS 2026 · similarity 0.84)
- Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption (CVPR 2025 · similarity 0.84)
- R4-CGQA: Retrieval-based Vision Language Models for Computer Graphics Image Quality Assessment (CVPR 2026 · similarity 0.84)
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.
