mlsanityData to 7 Oct 2026

CrossScore: Towards Multi-View Image Evaluation and Scoring

arXiv 2404.14409 ↗First posted 22 Apr 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

We introduce a novel cross-reference image quality assessment method that effectively fills the gap in the image assessment landscape, complementing the array of established evaluation schemes -- ranging from full-reference metrics like SSIM, no-reference metrics such as NIQE, to general-reference metrics including FID, and Multi-modal-reference metrics, e.g., CLIPScore. Utilising a neural network with the cross-attention mechanism and a unique data collection pipeline from NVS optimisation, our method enables accurate image quality assessment without requiring ground truth references. By comparing a query image against multiple views of the same scene, our method addresses the limitations of existing metrics in novel view synthesis (NVS) and similar tasks where direct reference images are unavailable. Experimental results show that our method is closely correlated to the full-reference metric SSIM, while not requiring ground truth references.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 50 of its 72 references that are in the map. First posted on arXiv 22 Apr 2024.

Builds on

50 of 72 references.

References · 50

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  8. 2016Improved Techniques for Training GANscited by 2,938
  9. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  10. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  11. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  12. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
38 more
  1. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  2. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  3. 2018Demystifying MMD GANscited by 1,268
  4. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  5. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  6. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  7. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  8. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  9. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  10. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  11. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  12. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  13. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 276
  14. 2021Urban Radiance Fieldscited by 263
  15. 2021BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Renderingcited by 228
  16. 2018A Note on the Inception Scorecited by 225
  17. 2020The EPIC-KITCHENS Dataset: Collection, Challenges and Baselinescited by 221
  18. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  19. 2021Self-Calibrating Neural Radiance Fieldscited by 204
  20. 2023Project Aria: A New Tool for Egocentric Multi-Modal AI Researchcited by 201
  21. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  22. 2013Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Indexcited by 193
  23. 2023Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perceptioncited by 166
  24. 2023Optimal Transport Aggregation for Visual Place Recognitioncited by 151
  25. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 112
  26. 2023Improving Multimodal Datasets with Image Captioningcited by 93
  27. 2018An empirical study on evaluation metrics of generative adversarial networkscited by 81
  28. 2021FoV-NeRF: Foveated Neural Radiance Fields for Virtual Realitycited by 79
  29. 2020Transformer for Image Quality Assessmentcited by 76
  30. 2024CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognitioncited by 61
  31. 2023DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fieldscited by 60
  32. 2021NeuralDiff: Segmenting 3D objects that move in egocentric videoscited by 56
  33. 2023CamP: Camera Preconditioning for Neural Radiance Fieldscited by 55
  34. 2023PoRF: Pose Residual Field for Accurate Neural Surface Reconstructioncited by 19
  35. 2022ScanNeRF: a Scalable Benchmark for Neural Radiance Fieldscited by 14
  36. 2023Benchmarking Robustness in Neural Radiance Fieldscited by 13
  37. 2023Aria-NeRF: Multimodal Egocentric View Synthesiscited by 4
  38. 2023Towards a Robust Framework for NeRF Evaluationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 3.

5 papers.

  1. 2024Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructionscited by 3
  2. 2026SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selectioncited by 2
  3. 2025Non-Aligned Reference Image Quality Assessment for Novel View Synthesiscited by 1
  4. 2026PR-IQA: Partial-Reference Image Quality Assessment for Diffusion-Based Novel View Synthesiscited by 0
  5. 2026From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessmentcited by 0