Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| 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 |