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.
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.
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.
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.
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.
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.
DarSwin‑Unet: Distortion Aware Encoder‑Decoder Architecture
An encoder-decoder architecture with distortion-aware transformer layers designed for omnidirectional tasks.
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.
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.
Circular Convolutional Neural Network
Proposes circular convolution and transposed convolution layers for panoramic imagery with wrap-around padding.
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.
Geometry Aware Convolutional Filters For Omnidirectional Images Representation
Proposes spatially adaptive filters that account for equirectangular distortion in omnidirectional image processing.
Omnidirectional Vision: Unified Model Using Conformal Geometry
Unified geometric model using conformal algebra to treat catadioptric and panoramic imaging systems in robotics.
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.
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.
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.
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.
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.
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.
360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization
Benchmark dataset and tools for cross-device 360° localization with equirectangular and pinhole image queries.
OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions
Optimizes spherical SDFs structured in adaptive binoctrees to reconstruct scenes from short 360° video sweeps.
Herglotz-NET: Implicit Neural Representation of Spherical Data
Models spherical signals using harmonic positional encoding for compact implicit neural representation of panoramic data.
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.
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.
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.
SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting
Jointly optimizes camera parameters and splatting for uncalibrated omnidirectional inputs without prior intrinsics.
Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction
Includes lens distortion modeling and cubemap resampling to reconstruct accurate views from fisheye imagery.
Free360: Layered Gaussian Splatting from Sparse and Unposed Views
Sparse-view 360° reconstruction using uncertainty-aware optimization and stereo bootstrapping in layered splatting.
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.
An Integrated 6DoF Video Camera and System Design
Facebook’s design for a synchronized multi-view 6DoF camera with software integration for immersive content.
Plenoptic 3D Vision System
An advanced plenoptic system integrating RGB, IR, and depth sensors for accurate 3D capture in robotics and vision.
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.
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.
RomniStereo: Recurrent Omnidirectional Stereo Matching
Stereo depth estimation for omnidirectional image pairs using recurrent refinement and spherical cost volumes.
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.
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.
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.
Deep Synthesis and Exploration of Omnidirectional Stereoscopic Environments
Synthesizes stereoscopic environments from a single 360° image, enabling immersive navigation using MCOP images.
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.
Deep Learning for Omnidirectional Vision: A Survey and New Perspectives
Comprehensive survey of deep learning in omnidirectional vision covering datasets, methods, and future challenges.