CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Jiale, Li, Jungang, Yu, Jieming, Yu, Xinglin, Dongfang, Zihao, Ding, Zongjian, Ding, Kaifeng, Yang, Yi, Chen, Lidong, Zou, Yang, Bai, Shunwen, Zhang, Jiahuan, Huang, Haoran, Huang, Shan, Gao, Yudong, Cheng, Mingjun
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910223497691136
author Liu, Jiale
Li, Jungang
Yu, Jieming
Yu, Xinglin
Dongfang, Zihao
Ding, Zongjian
Ding, Kaifeng
Yang, Yi
Chen, Lidong
Zou, Yang
Bai, Shunwen
Zhang, Jiahuan
Huang, Haoran
Huang, Shan
Gao, Yudong
Cheng, Mingjun
author_facet Liu, Jiale
Li, Jungang
Yu, Jieming
Yu, Xinglin
Dongfang, Zihao
Ding, Zongjian
Ding, Kaifeng
Yang, Yi
Chen, Lidong
Zou, Yang
Bai, Shunwen
Zhang, Jiahuan
Huang, Haoran
Huang, Shan
Gao, Yudong
Cheng, Mingjun
contents Modern 3D visual learning relies on observations sampled from metric 3D assets, yet existing scans, meshes, point clouds, simulations, and reconstructions do not directly provide a sparse, comparable, and geometry-consistent panoramic training interface. Dense trajectories duplicate nearby views, source-specific rendering policies yield heterogeneous annotations, and sparse heuristics may miss important regions or introduce depth-inconsistent observations. We study how to convert 3D assets into sparse panoramic RGB-D-pose data that preserves complete scene coverage with low redundancy and auditable provenance. We propose COVER (Coverage-Oriented Viewpoint curation with ERP Range-depth warping), a training-free ERP viewpoint curator that projects geometry observed from selected views into candidate ERP probes, scores incremental coverage, and penalizes depth conflicts. Under bounded proxy error, its greedy coverage proxy preserves the standard coverage-style approximation behavior up to an additive error term. Using COVER, we build CM-EVS (Coverage-curated Metric ERP View Set), a panoramic RGB-D-pose dataset with 36,373 curated ERP frames from 1,275 indoor scenes across Blender indoor, HM3D, and ScanNet++, complemented by outdoor panoramas from TartanGround and OB3D re-encoded into the same schema. Each frame provides full-sphere RGB, metric range depth, calibrated pose; COVER-produced indoor frames include per-step provenance logs. With a median of only 25 frames per indoor scene, CM-EVS covers all 13 unified room types while maintaining compact scene-level coverage. Experiments show that COVER improves the coverage-conflict trade-off, making CM-EVS a sparse, compact, and auditable RGB-D-pose resource for geometry-consistent panoramic 3D learning.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15597
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage
Liu, Jiale
Li, Jungang
Yu, Jieming
Yu, Xinglin
Dongfang, Zihao
Ding, Zongjian
Ding, Kaifeng
Yang, Yi
Chen, Lidong
Zou, Yang
Bai, Shunwen
Zhang, Jiahuan
Huang, Haoran
Huang, Shan
Gao, Yudong
Cheng, Mingjun
Computer Vision and Pattern Recognition
Graphics
Machine Learning
Robotics
Modern 3D visual learning relies on observations sampled from metric 3D assets, yet existing scans, meshes, point clouds, simulations, and reconstructions do not directly provide a sparse, comparable, and geometry-consistent panoramic training interface. Dense trajectories duplicate nearby views, source-specific rendering policies yield heterogeneous annotations, and sparse heuristics may miss important regions or introduce depth-inconsistent observations. We study how to convert 3D assets into sparse panoramic RGB-D-pose data that preserves complete scene coverage with low redundancy and auditable provenance. We propose COVER (Coverage-Oriented Viewpoint curation with ERP Range-depth warping), a training-free ERP viewpoint curator that projects geometry observed from selected views into candidate ERP probes, scores incremental coverage, and penalizes depth conflicts. Under bounded proxy error, its greedy coverage proxy preserves the standard coverage-style approximation behavior up to an additive error term. Using COVER, we build CM-EVS (Coverage-curated Metric ERP View Set), a panoramic RGB-D-pose dataset with 36,373 curated ERP frames from 1,275 indoor scenes across Blender indoor, HM3D, and ScanNet++, complemented by outdoor panoramas from TartanGround and OB3D re-encoded into the same schema. Each frame provides full-sphere RGB, metric range depth, calibrated pose; COVER-produced indoor frames include per-step provenance logs. With a median of only 25 frames per indoor scene, CM-EVS covers all 13 unified room types while maintaining compact scene-level coverage. Experiments show that COVER improves the coverage-conflict trade-off, making CM-EVS a sparse, compact, and auditable RGB-D-pose resource for geometry-consistent panoramic 3D learning.
title CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage
topic Computer Vision and Pattern Recognition
Graphics
Machine Learning
Robotics
url https://arxiv.org/abs/2605.15597