# Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning

arXiv: https://arxiv.org/abs/2109.10563 · HTML: https://mlsanity.com/paper/2109.10563/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 22 Sep 2021.

## Builds on (most cited first, 27 of 27)

- [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)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling](https://mlsanity.com/paper/1908.00222/) (2019)
- [Single-Image Depth Perception in the Wild](https://mlsanity.com/paper/1604.03901/) (2016)
- [Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras](https://mlsanity.com/paper/1904.04998/) (2019)
- [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)
- [Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes](https://mlsanity.com/paper/1904.11112/) (2019)
- [Cube Padding for Weakly-Supervised Saliency Prediction in 360deg Videos](https://mlsanity.com/paper/1806.01320/) (2018)
- [Spherical View Synthesis for Self-Supervised 360 Depth Estimation](https://mlsanity.com/paper/1909.08112/) (2019)
- [Self-Supervised Learning of Depth and Camera Motion from 360deg Videos](https://mlsanity.com/paper/1811.05304/) (2018)
- [360SD-Net: 360deg Stereo Depth Estimation with Learnable Cost Volume](https://mlsanity.com/paper/1911.04460/) (2019)
- [Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360deg Panoramic Imagery](https://mlsanity.com/paper/1808.06253/) (2018)
- [UprightNet: Geometry-Aware Camera Orientation Estimation from Single Images](https://mlsanity.com/paper/1908.07070/) (2019)
- [Mirror3D: Depth Refinement for Mirror Surfaces](https://mlsanity.com/paper/2106.06629/) (2021)

## Built on by (most cited first, 19 of 19)

- [PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation](https://mlsanity.com/paper/2203.09283/) (2022)
- [Review on Panoramic Imaging and Its Applications in Scene Understanding](https://mlsanity.com/paper/2205.05570/) (2022)
- [EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation](https://mlsanity.com/paper/2304.07803/) (2023)
- [Deep Learning for Omnidirectional Vision: A Survey and New Perspectives](https://mlsanity.com/paper/2205.10468/) (2022)
- [A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision](https://mlsanity.com/paper/2502.10444/) (2025)
- [Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion](https://mlsanity.com/paper/2203.09855/) (2022)
- [GLPanoDepth: Global-to-Local Panoramic Depth Estimation](https://mlsanity.com/paper/2202.02796/) (2022)
- [Panoramic Vision Transformer for Saliency Detection in 360deg Videos](https://mlsanity.com/paper/2209.08956/) (2022)
- [SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception](https://mlsanity.com/paper/2412.06968/) (2024)
- [SGFormer: Spherical Geometry Transformer for 360 Depth Estimation](https://mlsanity.com/paper/2404.14979/) (2024)
- [LDM3D-VR: Latent Diffusion Model for 3D VR](https://mlsanity.com/paper/2311.03226/) (2023)
- [METER: a mobile vision transformer architecture for monocular depth estimation](https://mlsanity.com/paper/2403.08368/) (2024)
- [EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching](https://mlsanity.com/paper/2502.20685/) (2025)
- [HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model](https://mlsanity.com/paper/2204.05007/) (2022)
- [RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization](https://mlsanity.com/paper/2509.23991/) (2025)
- [HDPV-SLAM: Hybrid Depth-augmented Panoramic Visual SLAM for Mobile Mapping System with Tilted LiDAR and Panoramic Visual Camera](https://mlsanity.com/paper/2301.11823/) (2023)
- [A Dual-Cycled Cross-View Transformer Network for Unified Road Layout Estimation and 3D Object Detection in the Bird's-Eye-View](https://mlsanity.com/paper/2209.08844/) (2022)
- [CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation](https://mlsanity.com/paper/2511.16428/) (2025)
- [Windowed-FourierMixer: Enhancing Clutter-Free Room Modeling with Fourier Transform](https://mlsanity.com/paper/2402.18287/) (2024)

## Abstract (arXiv)

Due to difficulties in acquiring ground truth depth of equirectangular (360) images, the quality and quantity of equirectangular depth data today is insufficient to represent the various scenes in the world. Therefore, 360 depth estimation studies, which relied solely on supervised learning, are destined to produce unsatisfactory results. Although self-supervised learning methods focusing on equirectangular images (EIs) are introduced, they often have incorrect or non-unique solutions, causing unstable performance. In this paper, we propose 360 monocular depth estimation methods which improve on the areas that limited previous studies. First, we introduce a self-supervised 360 depth learning method that only utilizes gravity-aligned videos, which has the potential to eliminate the needs for depth data during the training procedure. Second, we propose a joint learning scheme realized by combining supervised and self-supervised learning. The weakness of each learning is compensated, thus leading to more accurate depth estimation. Third, we propose a non-local fusion block, which can further retain the global information encoded by vision transformer when reconstructing the depths. With the proposed methods, we successfully apply the transformer to 360 depth estimations, to the best of our knowledge, which has not been tried before. On several benchmarks, our approach achieves significant improvements over previous works and establishes a state of the art.