Panoramic and Omnidirectional Vision Papers

DeepView: View Synthesis with Learned Gradient Descent
Proposes a learned gradient descent approach for producing multiplane images (MPIs) from sparse input views, enabling accurate scene reconstruction including occlusions and reflections.
Authors: John Flynn, Michael Broxton, Paul E. Debevec, et al.
Year & URL: 2019 — arXiv
Immersive Light Field Video with a Layered Mesh Representation
Full pipeline to capture and render immersive light field video using a 46-camera hemispherical rig for volumetric rendering.
Authors: Michael Broxton, John Flynn, Ryan Overbeck, et al.
Year & URL: 2020 — Project
A System for Acquiring, Processing, and Rendering Panoramic Light Field Stills for Virtual Reality
Portable capture and rendering system for panoramic light field stills with disk-based blending and VP9 compression for VR.
Authors: Ryan S. Overbeck, Daniel Erickson, Daniel Evangelakos, et al.
Year & URL: 2018 — arXiv
The Making of Welcome to Light Fields VR
Details the camera rigs and software pipeline behind Google’s immersive light field VR experience for SteamVR.
Authors: Ryan Overbeck, Daniel Erickson
Year & URL: 2018 — ACM
Taming Stable Diffusion for Text to 360° Panorama Image Generation
PanFusion combines Stable Diffusion with panoramic-aware attention for generating 360° images from text prompts.
Authors: Cheng Zhang, Qianyi Wu, Camilo Cruz Gambardella, et al.
Year & URL: 2024 — arXiv
360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model
360DVD presents a diffusion model with a 360-adapter for generating controllable panoramic video from text or prompts.
Authors: Qian Wang, Weiqi Li, Chong Mou, et al.
Year & URL: 2024 — arXiv
DarSwin‑Unet: Distortion Aware Encoder‑Decoder Architecture
An encoder-decoder architecture with distortion-aware transformer layers designed for omnidirectional tasks.
Authors: Akshaya Athwale, Ichrak Shili, Émile Bergeron, et al.
Year & URL: 2024 — arXiv
Imagine360: Immersive 360 Video Generation from Perspective Anchor
Framework to generate full 360° video from a standard camera anchor using dual-branch denoising and antipodal masking.
Authors: Jing Tan, Shuai Yang, Tong Wu, et al.
Year & URL: 2024 — arXiv
360-Degree Panorama Generation from Few Unregistered NFoV Images
PanoDiff pipeline to stitch a full panorama from sparse, unregistered narrow-FOV images using angle prediction and diffusion.
Authors: Jionghao Wang, Ziyu Chen, Jun Ling, et al.
Year & URL: 2023 — ACM
Circular Convolutional Neural Network
Proposes circular convolution and transposed convolution layers for panoramic imagery with wrap-around padding.
Authors: Stefan Schubert, Peer Neubert, Johannes Pöschmann, et al.
Year & URL: 2019 — IEEE
360 Panorama Super-resolution using Deep Convolutional Networks
Applies CNN-based super-resolution to 360° images, enhancing quality especially around equatorial regions using weighted loss.
Authors: V. Fakour-Sevom, E. Guldogan, J.-K. Kämäräinen
Year & URL: 2018 — VISAPP
Geometry Aware Convolutional Filters For Omnidirectional Images Representation
Proposes spatially adaptive filters that account for equirectangular distortion in omnidirectional image processing.
Authors: Renata Khasanova, Pascal Frossard
Year & URL: 2019 — ICML
Omnidirectional Vision: Unified Model Using Conformal Geometry
Unified geometric model using conformal algebra to treat catadioptric and panoramic imaging systems in robotics.
Authors: Eduardo Bayro-Corrochano, Carlos López-Franco
Year & URL: 2004 — Springer
Pano2Room: Novel View Synthesis from a Single Indoor Panorama
Synthesizes novel 3D views from a single indoor 360° panorama using mesh reconstruction and Gaussian splatting.
Authors: Guo Pu, Yiming Zhao, Zhouhui Lian
Year & URL: 2024 — arXiv
Deep Panoramic Depth Prediction and Completion for Indoor Scenes
Lightweight network that completes sparse depth input into dense maps using panoramic RGB and dynamic feature fusion.
Authors: G. Pintore, E. Almansa, M. Agus, E. Gobbetti
Year & URL: 2024 — Springer
Automatic 3D Modeling and Exploration of Indoor Structures from Panoramic Imagery
Tutorial covering state-of-the-art 3D reconstruction methods using panoramic imagery in indoor scenes.
Authors: Giovanni Pintore, Claudio Mura, Fabio Ganovelli, et al.
Year & URL: 2024 — SIGGRAPH Asia
HPCCN Project: AI-based 3D Interior Building Model Creation Results
Summarizes 3D modeling methods from the HPCCN Spoke-9 project including floorplans, stereo, and structured geometry pipelines.
Authors: CRS4 HPCCN Team
Year & URL: 2025 — GitHub
Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation
Presents UBotNet for depth and normal prediction on real-world omnidirectional data using synthetic-to-real transfer.
Authors: Jay Bhanushali, Manivannan Muniyandi, Praneeth Chakravarthula
Year & URL: 2024 — arXiv
Integration of Point Clouds from 360° Videos and Deep Learning Techniques
Combines structure-from-motion and deep classification to document city centers using low-cost 360° video capture.
Authors: Y. Cao, M. Previtali, L. Barazzetti, M. Scaioni
Year & URL: 2022 — ISPRS Archives
360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization
Benchmark dataset and tools for cross-device 360° localization with equirectangular and pinhole image queries.
Authors: Huajian Huang, Changkun Liu, Yipeng Zhu, et al.
Year & URL: 2023 — arXiv
OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions
Optimizes spherical SDFs structured in adaptive binoctrees to reconstruct scenes from short 360° video sweeps.
Authors: Hakyeong Kim, Andreas Meuleman, Hyeonjoong Jang, et al.
Year & URL: 2024 — arXiv
Herglotz-NET: Implicit Neural Representation of Spherical Data
Models spherical signals using harmonic positional encoding for compact implicit neural representation of panoramic data.
Authors: Unknown
Year & URL: – — Unavailable
PERF: Panoramic Neural Radiance Field from a Single Panorama
Constructs panoramic NeRFs from a single 360° image using depth prediction and RGB-D inpainting to enable roaming.
Authors: Guangcong Wang, Peng Wang, Zhaoxi Chen, et al.
Year & URL: 2024 — arXiv
Splatter-360: Generalizable 360° Gaussian Splatting for Wide-baseline Images
Splatting method tailored for wide-baseline 360° data using spherical cost volumes and bi-projection encoders.
Authors: (Multiple authors)
Year & URL: 2024 — arXiv
360-GS: Layout-guided Panoramic Gaussian Splatting for Indoor Roaming
Leverages indoor layout priors to initialize 3D Gaussians more effectively in equirectangular space for VR roaming.
Authors: Jiayang Bai, Letian Huang, Jie Guo, et al.
Year & URL: 2024 — arXiv
SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting
Jointly optimizes camera parameters and splatting for uncalibrated omnidirectional inputs without prior intrinsics.
Authors: Huajian Huang, Yingshu Chen, Longwei Li, et al.
Year & URL: 2025 — arXiv
Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction
Includes lens distortion modeling and cubemap resampling to reconstruct accurate views from fisheye imagery.
Authors: Youming Deng, Wenqi Xian, Guandao Yang, et al.
Year & URL: 2025 — arXiv
Free360: Layered Gaussian Splatting from Sparse and Unposed Views
Sparse-view 360° reconstruction using uncertainty-aware optimization and stereo bootstrapping in layered splatting.
Authors: Chong Bao, Xiyu Zhang, Zehao Yu, et al.
Year & URL: 2025 — arXiv
A Low Cost Multi-Camera Array for Panoramic Light Field Video Capture
Describes a hemispherical camera rig using Yi 4K cameras to produce immersive 6-DoF video content.
Authors: Michael Broxton, John Flynn, Paul Debevec, et al.
Year & URL: 2019 — Google
An Integrated 6DoF Video Camera and System Design
Facebook’s design for a synchronized multi-view 6DoF camera with software integration for immersive content.
Authors: Yash Patel, et al. (Facebook Reality Labs)
Year & URL: 2019 — Meta
Plenoptic 3D Vision System
An advanced plenoptic system integrating RGB, IR, and depth sensors for accurate 3D capture in robotics and vision.
Authors: Vahe Taamazyan, et al. (Intrinsic)
Year & URL: 2024 — Intrinsic
RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching
Stereo depth estimation using a recurrent matching module based on RAFT, achieving high accuracy on Scene Flow and KITTI.
Authors: Zachary Teed, Jia Deng
Year & URL: 2021 — arXiv
Depth Augmented Omnidirectional Stereo for 6-DoF VR Photography
Augments stereo panoramas with depth to enable parallax and VR navigation in 6-DoF from a single panoramic pair.
Authors: Tobias Bertel, Moritz Mühlhausen, et al.
Year & URL: 2020 — ACM
RomniStereo: Recurrent Omnidirectional Stereo Matching
Stereo depth estimation for omnidirectional image pairs using recurrent refinement and spherical cost volumes.
Authors: Hualie Jiang, Rui Xu, Minglang Tan, Wenjie Jiang
Year & URL: 2024 — arXiv
OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching
Learns stereo depth on omnidirectional images via concentric spherical warping and 3D convolutions over the sweep volume.
Authors: Changhee Won, Jongbin Ryu, Jongwoo Lim
Year & URL: 2019 — ICCV
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume
A spherical stereo depth model using learnable disparity cost volumes tailored for top-bottom 360° image pairs.
Authors: Ning-Hsu Wang, Bolivar Solarte, et al.
Year & URL: 2020 — arXiv
Estimating Depth of Monocular Panoramic Image With Teacher-Student Model
Uses spherical convolution and dual-representation teacher-student training to estimate depth from a single panorama.
Authors: Jingguo Liu, Yijun Xu, Shigang Li, Jianfeng Li
Year & URL: 2024 — arXiv
Deep Synthesis and Exploration of Omnidirectional Stereoscopic Environments
Synthesizes stereoscopic environments from a single 360° image, enabling immersive navigation using MCOP images.
Authors: Giovanni Pintore, Alberto Jaspe-Villanueva, et al.
Year & URL: 2024 — Computers & Graphics
Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?
Benchmarks GPT-4o and others on spatial reasoning tasks in omnidirectional scenes using OSR-Bench dataset.
Authors: Zihao Dongfang, Xu Zheng, Ziqiao Weng, et al.
Year & URL: 2025 — arXiv
Deep Learning for Omnidirectional Vision: A Survey and New Perspectives
Comprehensive survey of deep learning in omnidirectional vision covering datasets, methods, and future challenges.
Authors: Hao Ai, Zidong Cao, Jinjing Zhu, et al.
Year & URL: 2022 — arXiv