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

arXiv 25.09 2025 39.2 method

TLDR

Survey on panoramic vision techniques focusing on perspective-to-panorama adaptation, covering challenges and 20+ tasks.

Reasoning

The paper provides a comprehensive survey of panoramic vision adaptation, systematically reviewing geometric distortions, non-uniform sampling, and boundary continuity across many tasks. However, as a survey, it lacks novel experiments or empirical contributions, limiting its direct impact.

Read-first score

Read-first score 39.2, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 0.

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=analysis,experiment,metric,validation

Recency 8%

86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=github

Topical relevance 42%

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 383.

Keyword Scores

world model

world simulator

generative world model

interactive world model

video world model

world dynamics prediction

model-based reinforcement learning world model

Deep Analysis

Innovations

Systematic categorization of panoramic vision into four major categories: visual quality enhancement and assessment, visual understanding, multimodal understanding, and visual generation.
Cross-method analysis of strategies addressing panoramic-specific challenges (geometric distortions, non-uniform sampling, periodic boundary continuity) across different tasks.
Cross-task comparison and classification of panoramic vision research, covering 20+ representative tasks from over 300 papers.

Methodology

The survey revisits the panoramic imaging pipeline and projection methods to establish prior knowledge, then summarizes three key challenges of perspective-to-panorama adaptation: severe geometric distortions near the poles, non-uniform sampling in Equirectangular Projection (ERP), and periodic boundary continuity. It covers 20+ representative tasks from over 300 research papers, presenting a cross-method analysis of strategies and a cross-task comparison, and classifies panoramic vision into four major categories.

Key Results

The survey identifies three core challenges for domain adaptation from perspective to panoramic vision and categorizes the field into four major areas: visual quality enhancement and assessment, visual understanding, multimodal understanding, and visual generation.

Limitations

The survey is a review of existing literature and does not propose new methods or experimental validation.
The coverage of 20+ representative tasks may not be exhaustive of all panoramic vision research.
Open challenges and future directions in data, models, and applications are discussed but not resolved.

Resources

Paper Page