mlsanityData to 7 Oct 2026

Geometry Fidelity for Spherical Images

arXiv 2407.18207 ↗First posted 25 Jul 2024cs.CV cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Spherical or omni-directional images offer an immersive visual format appealing to a wide range of computer vision applications. However, geometric properties of spherical images pose a major challenge for models and metrics designed for ordinary 2D images. Here, we show that direct application of Fr'echet Inception Distance (FID) is insufficient for quantifying geometric fidelity in spherical images. We introduce two quantitative metrics accounting for geometric constraints, namely Omnidirectional FID (OmniFID) and Discontinuity Score (DS). OmniFID is an extension of FID tailored to additionally capture field-of-view requirements of the spherical format by leveraging cubemap projections. DS is a kernel-based seam alignment score of continuity across borders of 2D representations of spherical images. In experiments, OmniFID and DS quantify geometry fidelity issues that are undetected by FID.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 17 of its 36 references that are in the map. First posted on arXiv 25 Jul 2024.

Builds on

17 of 36 references.

References · 17

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  5. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
  6. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 303
  7. 2019Effectively Unbiased FID and Inception Score and where to find themcited by 161
  8. 2017Learning to Predict Indoor Illumination from a Single Imagecited by 160
  9. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 121
  10. 2019Tangent Images for Mitigating Spherical Distortioncited by 79
  11. 2022Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creationcited by 47
  12. 2023360-Degree Panorama Generation from Few Unregistered NFoV Imagescited by 42
5 more
  1. 2023Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generationcited by 33
  2. 2019360-Indoor: Towards Learning Real-World Objects in 360deg Indoor Equirectangular Imagescited by 25
  3. 2019Convolutions on Spherical Imagescited by 12
  4. 2021Evaluating generative networks using Gaussian mixtures of image featurescited by 11
  5. 2021A Survey on 360-Degree Video: Coding, Quality of Experience and Streamingcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 4.

9 papers.

  1. 2024Imagine360: Immersive 360 Video Generation from Perspective Anchorcited by 27
  2. 2025PanoWan: Lifting Diffusion Video Generation Models to 360deg with Latitude/Longitude-aware Mechanismscited by 22
  3. 2025Conditional Panoramic Image Generation via Masked Autoregressive Modelingcited by 9
  4. 2026360Anything: Geometry-Free Lifting of Images and Videos to 360degcited by 7
  5. 2025TanDiT: Tangent-Plane Diffusion Transformer for High-Quality 360deg Panorama Generationcited by 3
  6. 2026SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPEcited by 2
  7. 2025A Survey on Text-Driven 360-Degree Panorama Generationcited by 0
  8. 2026Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completioncited by 0
  9. 2026SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360^circ Panorama Generationcited by 0