OmniCoT is a new panoramic reasoning benchmark with 6.7K eval, 1K real, and 14.3K training examples plus a two-stage SFT+GRPO training method to enforce global 360-degree consistency.
One flight over the gap: A survey from perspective to panoramic vision
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
Driven by the demand for spatial intelligence and holistic scene perception, omnidirectional images (ODIs), which provide a complete 360\textdegree{} 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
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 8roles
background 1polarities
background 1representative citing papers
A geometry and gradient-based partitioning strategy enables scalable block-wise 3D Gaussian Splatting for large-scale panoramic outdoor scenes.
CylindTrack improves identity preservation in panoramic multi-object tracking by combining depth-temporal trajectory modeling, spherical spatio-temporal consistency learning, and topology-aware cylindrical motion prediction.
UniSHARP performs universal sharp monocular view synthesis by implicit alignment of diverse camera images in a unified omnidirectional latent space using ray-arranged Gaussian primitives and UniK3D-inspired feature decoding.
PanoGSDet projects panoramic 2D features into optimized semantic 3D Gaussians to generate accurate 3D bounding boxes, outperforming prior methods on the Structured3D dataset.
PanoWorld adds spherical spatial cross-attention and pano-native training data to MLLMs for improved spatial reasoning on ERP panoramas, outperforming baselines on new and existing benchmarks.
OmniTrack++ improves omnidirectional multi-object tracking with trajectory feedback through DynamicSSM stabilization, FlexiTrack instances, ExpertTrack Memory with Mixture-of-Experts, and adaptive Tracklet Management, achieving SOTA HOTA gains on JRDB and new EmboTrack benchmark.
A survey diagnosing panoramic scene understanding as a field that converged on compatibility-preserving geometric adaptation rather than sphere-native modeling, while its evaluation protocols systematically fail to measure spherical understanding.
citing papers explorer
-
OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning
OmniCoT is a new panoramic reasoning benchmark with 6.7K eval, 1K real, and 14.3K training examples plus a two-stage SFT+GRPO training method to enforce global 360-degree consistency.
-
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
A geometry and gradient-based partitioning strategy enables scalable block-wise 3D Gaussian Splatting for large-scale panoramic outdoor scenes.
-
CylindTrack: Depth-Aware Cylindrical Motion Modeling for Panoramic Multi-Object Tracking
CylindTrack improves identity preservation in panoramic multi-object tracking by combining depth-temporal trajectory modeling, spherical spatio-temporal consistency learning, and topology-aware cylindrical motion prediction.
-
UniSHARP: Universal Sharp Monocular View Synthesis
UniSHARP performs universal sharp monocular view synthesis by implicit alignment of diverse camera images in a unified omnidirectional latent space using ray-arranged Gaussian primitives and UniK3D-inspired feature decoding.
-
Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach
PanoGSDet projects panoramic 2D features into optimized semantic 3D Gaussians to generate accurate 3D bounding boxes, outperforming prior methods on the Structured3D dataset.
-
PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World
PanoWorld adds spherical spatial cross-attention and pano-native training data to MLLMs for improved spatial reasoning on ERP panoramas, outperforming baselines on new and existing benchmarks.
-
OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback
OmniTrack++ improves omnidirectional multi-object tracking with trajectory feedback through DynamicSSM stabilization, FlexiTrack instances, ExpertTrack Memory with Mixture-of-Experts, and adaptive Tracklet Management, achieving SOTA HOTA gains on JRDB and new EmboTrack benchmark.
-
Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling
A survey diagnosing panoramic scene understanding as a field that converged on compatibility-preserving geometric adaptation rather than sphere-native modeling, while its evaluation protocols systematically fail to measure spherical understanding.