Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Xin, Song, Meixi, Zhang, Dizhe, Lu, Wenxuan, Li, Haodong, Du, Bo, Yang, Ming-Hsuan, Nguyen, Truong, Qi, Lu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912774436683776
author Lin, Xin
Song, Meixi
Zhang, Dizhe
Lu, Wenxuan
Li, Haodong
Du, Bo
Yang, Ming-Hsuan
Nguyen, Truong
Qi, Lu
author_facet Lin, Xin
Song, Meixi
Zhang, Dizhe
Lu, Wenxuan
Li, Haodong
Du, Bo
Yang, Ming-Hsuan
Nguyen, Truong
Qi, Lu
contents In this work, we present a panoramic metric depth foundation model that generalizes across diverse scene distances. We explore a data-in-the-loop paradigm from the view of both data construction and framework design. We collect a large-scale dataset by combining public datasets, high-quality synthetic data from our UE5 simulator and text-to-image models, and real panoramic images from the web. To reduce domain gaps between indoor/outdoor and synthetic/real data, we introduce a three-stage pseudo-label curation pipeline to generate reliable ground truth for unlabeled images. For the model, we adopt DINOv3-Large as the backbone for its strong pre-trained generalization, and introduce a plug-and-play range mask head, sharpness-centric optimization, and geometry-centric optimization to improve robustness to varying distances and enforce geometric consistency across views. Experiments on multiple benchmarks (e.g., Stanford2D3D, Matterport3D, and Deep360) demonstrate strong performance and zero-shot generalization, with particularly robust and stable metric predictions in diverse real-world scenes. The project page can be found at: \href{https://insta360-research-team.github.io/DAP_website/} {https://insta360-research-team.github.io/DAP\_website/}
format Preprint
id arxiv_https___arxiv_org_abs_2512_16913
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation
Lin, Xin
Song, Meixi
Zhang, Dizhe
Lu, Wenxuan
Li, Haodong
Du, Bo
Yang, Ming-Hsuan
Nguyen, Truong
Qi, Lu
Computer Vision and Pattern Recognition
In this work, we present a panoramic metric depth foundation model that generalizes across diverse scene distances. We explore a data-in-the-loop paradigm from the view of both data construction and framework design. We collect a large-scale dataset by combining public datasets, high-quality synthetic data from our UE5 simulator and text-to-image models, and real panoramic images from the web. To reduce domain gaps between indoor/outdoor and synthetic/real data, we introduce a three-stage pseudo-label curation pipeline to generate reliable ground truth for unlabeled images. For the model, we adopt DINOv3-Large as the backbone for its strong pre-trained generalization, and introduce a plug-and-play range mask head, sharpness-centric optimization, and geometry-centric optimization to improve robustness to varying distances and enforce geometric consistency across views. Experiments on multiple benchmarks (e.g., Stanford2D3D, Matterport3D, and Deep360) demonstrate strong performance and zero-shot generalization, with particularly robust and stable metric predictions in diverse real-world scenes. The project page can be found at: \href{https://insta360-research-team.github.io/DAP_website/} {https://insta360-research-team.github.io/DAP\_website/}
title Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.16913