# SGFormer: Spherical Geometry Transformer for 360 Depth Estimation

arXiv: https://arxiv.org/abs/2404.14979 · HTML: https://mlsanity.com/paper/2404.14979/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 65 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [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)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling](https://mlsanity.com/paper/1908.00222/) (2019)
- [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)
- [UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimation](https://mlsanity.com/paper/2102.03550/) (2021)
- [Spherical CNNs on Unstructured Grids](https://mlsanity.com/paper/1901.02039/) (2019)
- [Tangent Images for Mitigating Spherical Distortion](https://mlsanity.com/paper/1912.09390/) (2019)
- [Cube Padding for Weakly-Supervised Saliency Prediction in 360deg Videos](https://mlsanity.com/paper/1806.01320/) (2018)
- [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)
- [Kernel Transformer Networks for Compact Spherical Convolution](https://mlsanity.com/paper/1812.03115/) (2018)
- [EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation](https://mlsanity.com/paper/2304.07803/) (2023)
- [SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Images](https://mlsanity.com/paper/1811.08196/) (2018)
- [Self-Supervised Learning of Depth and Camera Motion from 360deg Videos](https://mlsanity.com/paper/1811.05304/) (2018)
- [Pano3D: A Holistic Benchmark and a Solid Baseline for 360o Depth Estimation](https://mlsanity.com/paper/2109.02749/) (2021)
- [HRDFuse: Monocular 360degDepth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributions](https://mlsanity.com/paper/2303.11616/) (2023)
- [BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation](https://mlsanity.com/paper/2209.02952/) (2022)
- [Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion](https://mlsanity.com/paper/2403.16376/) (2024)
- [PanoSwin: a Pano-style Swin Transformer for Panorama Understanding](https://mlsanity.com/paper/2308.14726/) (2023)

## Built on by (most cited first, 9 of 9)

- [PanoNormal: Monocular Indoor 360deg Surface Normal Estimation](https://mlsanity.com/paper/2405.18745/) (2024)
- [VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation](https://mlsanity.com/paper/2603.18943/) (2026)
- [Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling](https://mlsanity.com/paper/2606.27745/) (2026)
- [MCPDepth: Omnidirectional Depth Estimation via Stereo Matching from Multi-Cylindrical Panoramas](https://mlsanity.com/paper/2408.01653/) (2024)
- [Semi-Supervised 360 Layout Estimation with Panoramic Collaborative Perturbations](https://mlsanity.com/paper/2503.01114/) (2025)
- [PAGCNet: A Pose-Aware and Geometry Constrained Framework for Panoramic Depth Estimation](https://mlsanity.com/paper/2510.07817/) (2025)
- [Neural Operators for Biomedical Spherical Heterogeneity](https://mlsanity.com/paper/2601.03561/) (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)

## Abstract (arXiv)

Panoramic distortion poses a significant challenge in 360 depth estimation, particularly pronounced at the north and south poles. Existing methods either adopt a bi-projection fusion strategy to remove distortions or model long-range dependencies to capture global structures, which can result in either unclear structure or insufficient local perception. In this paper, we propose a spherical geometry transformer, named SGFormer, to address the above issues, with an innovative step to integrate spherical geometric priors into vision transformers. To this end, we retarget the transformer decoder to a spherical prior decoder (termed SPDecoder), which endeavors to uphold the integrity of spherical structures during decoding. Concretely, we leverage bipolar re-projection, circular rotation, and curve local embedding to preserve the spherical characteristics of equidistortion, continuity, and surface distance, respectively. Furthermore, we present a query-based global conditional position embedding to compensate for spatial structure at varying resolutions. It not only boosts the global perception of spatial position but also sharpens the depth structure across different patches. Finally, we conduct extensive experiments on popular benchmarks, demonstrating our superiority over state-of-the-art solutions.