# PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation

arXiv: https://arxiv.org/abs/2406.13378 · HTML: https://mlsanity.com/paper/2406.13378/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 61 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Builds on (most cited first, 30 of 46)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image](https://mlsanity.com/paper/2307.10984/) (2023)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling](https://mlsanity.com/paper/1908.00222/) (2019)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation](https://mlsanity.com/paper/2307.14460/) (2023)
- [Semi-Supervised Deep Learning for Monocular Depth Map Prediction](https://mlsanity.com/paper/1702.02706/) (2017)
- [HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features](https://mlsanity.com/paper/2011.11498/) (2020)
- [OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas](https://mlsanity.com/paper/1807.09620/) (2018)
- [PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation](https://mlsanity.com/paper/2203.09283/) (2022)
- [USB: A Unified Semi-supervised Learning Benchmark for Classification](https://mlsanity.com/paper/2208.07204/) (2022)
- [UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimation](https://mlsanity.com/paper/2102.03550/) (2021)
- [OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion](https://mlsanity.com/paper/2203.00838/) (2022)
- [360MonoDepth: High-Resolution 360deg Monocular Depth Estimation](https://mlsanity.com/paper/2111.15669/) (2021)
- [Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective](https://mlsanity.com/paper/2303.13434/) (2023)

## Built on by (most cited first, 22 of 22)

- [DA2: Depth Anything in Any Direction](https://mlsanity.com/paper/2509.26618/) (2025)
- [Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation](https://mlsanity.com/paper/2512.16913/) (2025)
- [Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation](https://mlsanity.com/paper/2510.08673/) (2025)
- [PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery](https://mlsanity.com/paper/2603.17571/) (2026)
- [Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond](https://mlsanity.com/paper/2604.22482/) (2026)
- [VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation](https://mlsanity.com/paper/2603.18943/) (2026)
- [MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors](https://mlsanity.com/paper/2602.05330/) (2026)
- [EventVGGT: Exploring Cross-Modal Distillation for Consistent Event-based Depth Estimation](https://mlsanity.com/paper/2603.09385/) (2026)
- [PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World](https://mlsanity.com/paper/2605.13169/) (2026)
- [Depth Anything in 360^circ: Towards Scale Invariance in the Wild](https://mlsanity.com/paper/2512.22819/) (2025)
- [Unified Panoramic Geometry Estimation via Multi-View Foundation Models](https://mlsanity.com/paper/2605.26368/) (2026)
- [Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling](https://mlsanity.com/paper/2606.27745/) (2026)
- [Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes](https://mlsanity.com/paper/2606.30047/) (2026)
- [AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2608.29081/) (2026)
- [OmniPoint: Universal Monocular Metric Pointcloud from Any Camera](https://mlsanity.com/paper/2609.09394/) (2026)
- [Cross360: 360deg Monocular Depth Estimation via Cross Projections Across Scales](https://mlsanity.com/paper/2601.17271/) (2026)
- [RePer-360: Releasing Perspective Priors for 360^circ Depth Estimation via Self-Modulation](https://mlsanity.com/paper/2603.05999/) (2026)
- [H-OmniStereo: Zero-Shot Omnidirectional Stereo Matching with Heading-Aligned Normal Priors](https://mlsanity.com/paper/2605.14963/) (2026)
- [DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images](https://mlsanity.com/paper/2606.12368/) (2026)
- [Shear-Free Viewport Magnification for 360-Degree via Spherical Mobius Boosts](https://mlsanity.com/paper/2606.20684/) (2026)
- [Monocular Depth Estimation from a Single Image: Progress and Opportunities](https://mlsanity.com/paper/2609.01172/) (2026)
- [Feedforward Novel View Synthesis for Heterogeneous Cameras](https://mlsanity.com/paper/2610.03522/) (2026)

## Abstract (arXiv)

Recently, Depth Anything Models (DAMs) - a type of depth foundation models - have demonstrated impressive zero-shot capabilities across diverse perspective images. Despite its success, it remains an open question regarding DAMs' performance on panorama images that enjoy a large field-of-view (180x360) but suffer from spherical distortions. To address this gap, we conduct an empirical analysis to evaluate the performance of DAMs on panoramic images and identify their limitations. For this, we undertake comprehensive experiments to assess the performance of DAMs from three key factors: panoramic representations, 360 camera positions for capturing scenarios, and spherical spatial transformations. This way, we reveal some key findings, e.g., DAMs are sensitive to spatial transformations. We then propose a semi-supervised learning (SSL) framework to learn a panoramic DAM, dubbed PanDA. Under the umbrella of SSL, PanDA first learns a teacher model by fine-tuning DAM through joint training on synthetic indoor and outdoor panoramic datasets. Then, a student model is trained using large-scale unlabeled data, leveraging pseudo-labels generated by the teacher model. To enhance PanDA's generalization capability, M"obius transformation-based spatial augmentation (MTSA) is proposed to impose consistency regularization between the predicted depth maps from the original and spatially transformed ones. This subtly improves the student model's robustness to various spatial transformations, even under severe distortions. Extensive experiments demonstrate that PanDA exhibits remarkable zero-shot capability across diverse scenes, and outperforms the data-specific panoramic depth estimation methods on two popular real-world benchmarks.