One Flight Over the Gap: A Survey from Perspective to Panoramic Vision

2025-09-04

AI Summary

Existing domain adaptation methods fail on omnidirectional images (ODIs) due to fundamental geometric, sampling, and boundary differences—namely, projection distortion (e.g., pole singularities), non-uniform sampling density, and cyclic boundary conditions—compared to perspective images. To address this, this work establishes the first systematic cross-task classification taxonomy and cross-method analytical framework for panoramic vision. Grounded in equirectangular projection (ERP) geometry modeling, it comprehensively surveys over 300 works on distortion correction, adaptive sampling schemes, and specialized network architectures. The paper introduces a unified analytical perspective, maps the landscape of panoramic vision research, and clarifies open challenges across data, model, and application layers. It thereby provides theoretical foundations and developmental pathways for 360° visual understanding, multimodal fusion, and generative tasks, advancing spatial intelligence and holistic scene perception.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Driven by the demand for spatial intelligence and holistic scene perception, omnidirectional images (ODIs), which provide a complete 360 extdegree{} field of view, are receiving growing attention across diverse applications such as virtual reality, autonomous driving, and embodied robotics. Despite their unique characteristics, ODIs exhibit remarkable differences from perspective images in geometric projection, spatial distribution, and boundary continuity, making it challenging for direct domain adaption from perspective methods. This survey reviews recent panoramic vision techniques with a particular emphasis on the perspective-to-panorama adaptation. We first revisit the panoramic imaging pipeline and projection methods to build the prior knowledge required for analyzing the structural disparities. Then, we summarize three challenges of domain adaptation: severe geometric distortions near the poles, non-uniform sampling in Equirectangular Projection (ERP), and periodic boundary continuity. Building on this, we cover 20+ representative tasks drawn from more than 300 research papers in two dimensions. On one hand, we present a cross-method analysis of representative strategies for addressing panoramic specific challenges across different tasks. On the other hand, we conduct a cross-task comparison and classify panoramic vision into four major categories: visual quality enhancement and assessment, visual understanding, multimodal understanding, and visual generation. In addition, we discuss open challenges and future directions in data, models, and applications that will drive the advancement of panoramic vision research. We hope that our work can provide new insight and forward looking perspectives to advance the development of panoramic vision technologies. Our project page is https://insta360-research-team.github.io/Survey-of-Panorama

Problem

• Addressing domain adaptation challenges from perspective to panoramic images
• Overcoming geometric distortions and boundary issues in omnidirectional vision
• Surveying techniques for holistic scene perception in 360-degree applications

Innovation

• Surveying perspective-to-panoramic vision adaptation techniques
• Analyzing geometric distortions and boundary continuity challenges
• Classifying panoramic vision into four major categories