mlsanityData to 14 Oct 2026

Moving in a 360 World: Synthesizing Panoramic Parallaxes from a Single Panorama

arXiv 2106.10859 ↗First posted 21 Jun 2021cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

We present Omnidirectional Neural Radiance Fields (OmniNeRF), the first method to the application of parallax-enabled novel panoramic view synthesis. Recent works for novel view synthesis focus on perspective images with limited field-of-view and require sufficient pictures captured in a specific condition. Conversely, OmniNeRF can generate panorama images for unknown viewpoints given a single equirectangular image as training data. To this end, we propose to augment the single RGB-D panorama by projecting back and forth between a 3D world and different 2D panoramic coordinates at different virtual camera positions. By doing so, we are able to optimize an Omnidirectional Neural Radiance Field with visible pixels collecting from omnidirectional viewing angles at a fixed center for the estimation of new viewing angles from varying camera positions. As a result, the proposed OmniNeRF achieves convincing renderings of novel panoramic views that exhibit the parallax effect. We showcase the effectiveness of each of our proposals on both synthetic and real-world datasets.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 22 of its 40 references that are in the map. First posted on arXiv 21 Jun 2021.

Builds on

22 of 40 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  4. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  5. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  7. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  8. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  9. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  10. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  11. 2017Neural 3D Mesh Renderercited by 437
  12. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
10 more
  1. 2019Structured3D: A Large Photo-realistic Dataset for Structured 3D Modelingcited by 286
  2. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  3. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  4. 2019Neural Rerendering in the Wildcited by 121
  5. 2019Learning the Depths of Moving People by Watching Frozen Peoplecited by 120
  6. 2019HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentationcited by 108
  7. 2019Revealing Scenes by Inverting Structure from Motion Reconstructionscited by 66
  8. 2020Crowdsampling the Plenoptic Functioncited by 62
  9. 2015Multi-view 3D Models from Single Images with a Convolutional Networkcited by 58
  10. 2020Meshlet Priors for 3D Mesh Reconstructioncited by 23

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 6; 2023: 4; 2024: 5; 2025: 3.

19 papers.

Sort:

  1. 2021Neural Fields in Visual Computing and Beyondcited by 540
  2. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  3. 2022Removing Objects From Neural Radiance Fieldscited by 66
  4. 2023PERF: Panoramic Neural Radiance Field from a Single Panoramacited by 45
  5. 2022Deep Learning for Omnidirectional Vision: A Survey and New Perspectivescited by 38
  6. 2023Balanced Spherical Grid for Egocentric View Synthesiscited by 29
  7. 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 24
  8. 2022360FusionNeRF: Panoramic Neural Radiance Fields with Joint Guidancecited by 23
  9. 2024ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattingscited by 20
  10. 2024Pano2Room: Novel View Synthesis from a Single Indoor Panoramacited by 16
  11. 2022Casual Indoor HDR Radiance Capture from Omnidirectional Imagescited by 11
  12. 2022Enhancement of Novel View Synthesis Using Omnidirectional Image Completioncited by 9
7 more
  1. 2024PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Trainingcited by 4
  2. 2025ErpGS: Equirectangular Image Rendering enhanced with 3D Gaussian Regularizationcited by 4
  3. 2022OmniVoxel: A Fast and Precise Reconstruction Method of Omnidirectional Neural Radiance Fieldcited by 2
  4. 2024MaGRITTe: Manipulative and Generative 3D Realization from Image, Topview and Textcited by 2
  5. 2025You Need a Transition Plane: Bridging Continuous Panoramic 3D Reconstruction with Perspective Gaussian Splattingcited by 2
  6. 2023Enhancing Perception and Immersion in Pre-Captured Environments through Learning-Based Eye Height Adaptationcited by 1
  7. 2024MSI-NeRF: Linking Omni-Depth with View Synthesis through Multi-Sphere Image aided Generalizable Neural Radiance Fieldcited by 1