# Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention

arXiv: https://arxiv.org/abs/2210.09071 · HTML: https://mlsanity.com/paper/2210.09071/

## Key facts

- Cited by 93 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 37 references that are in the map.
- First posted on arXiv 17 Oct 2022.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [Enforcing geometric constraints of virtual normal for depth prediction](https://mlsanity.com/paper/1907.12209/) (2019)
- [MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation](https://mlsanity.com/paper/1902.04049/) (2019)
- [NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation](https://mlsanity.com/paper/2203.01502/) (2022)
- [Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction](https://mlsanity.com/paper/2103.12091/) (2021)
- [Semi-Supervised Deep Learning for Monocular Depth Map Prediction](https://mlsanity.com/paper/1702.02706/) (2017)
- [P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior](https://mlsanity.com/paper/2204.02091/) (2022)
- [Point Cloud Completion by Skip-attention Network with Hierarchical Folding](https://mlsanity.com/paper/2005.03871/) (2020)
- [Guiding Monocular Depth Estimation Using Depth-Attention Volume](https://mlsanity.com/paper/2004.02760/) (2020)
- [Structure-Aware Residual Pyramid Network for Monocular Depth Estimation](https://mlsanity.com/paper/1907.06023/) (2019)
- [Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion](https://mlsanity.com/paper/2103.16690/) (2021)
- [Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion](https://mlsanity.com/paper/2207.04535/) (2022)
- [CutDepth:Edge-aware Data Augmentation in Depth Estimation](https://mlsanity.com/paper/2107.07684/) (2021)
- [EdgeConv with Attention Module for Monocular Depth Estimation](https://mlsanity.com/paper/2106.08615/) (2021)
- [Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecture](https://mlsanity.com/paper/2207.04721/) (2022)

## Built on by (most cited first, 30 of 93)

- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation](https://mlsanity.com/paper/2306.01923/) (2023)
- [Towards Zero-Shot Scale-Aware Monocular Depth Estimation](https://mlsanity.com/paper/2306.17253/) (2023)
- [Monocular Depth Estimation using Diffusion Models](https://mlsanity.com/paper/2302.14816/) (2023)
- [DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation](https://mlsanity.com/paper/2303.05021/) (2023)
- [iDisc: Internal Discretization for Monocular Depth Estimation](https://mlsanity.com/paper/2304.06334/) (2023)
- [IEBins: Iterative Elastic Bins for Monocular Depth Estimation](https://mlsanity.com/paper/2309.14137/) (2023)
- [ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation](https://mlsanity.com/paper/2403.18807/) (2024)
- [Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN](https://mlsanity.com/paper/2308.08333/) (2023)
- [Self-supervised Monocular Depth Estimation: Let's Talk About The Weather](https://mlsanity.com/paper/2307.08357/) (2023)
- [Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model](https://mlsanity.com/paper/2312.13252/) (2023)
- [GEDepth: Ground Embedding for Monocular Depth Estimation](https://mlsanity.com/paper/2309.09975/) (2023)
- [MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation](https://mlsanity.com/paper/2307.14336/) (2023)
- [FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking Datasets](https://mlsanity.com/paper/2302.12772/) (2023)
- [Enhancing Diffusion Models with 3D Perspective Geometry Constraints](https://mlsanity.com/paper/2312.00944/) (2023)
- [Vision-Language Embodiment for Monocular Depth Estimation](https://mlsanity.com/paper/2503.16535/) (2025)
- [Single Image Depth Prediction Made Better: A Multivariate Gaussian Take](https://mlsanity.com/paper/2303.18164/) (2023)
- [Learnable Differencing Center for Nighttime Depth Perception](https://mlsanity.com/paper/2306.14538/) (2023)
- [EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment](https://mlsanity.com/paper/2312.08548/) (2023)
- [Harnessing Diffusion Models for Visual Perception with Meta Prompts](https://mlsanity.com/paper/2312.14733/) (2023)
- [FutureDepth: Learning to Predict the Future Improves Video Depth Estimation](https://mlsanity.com/paper/2403.12953/) (2024)
- [The Second Monocular Depth Estimation Challenge](https://mlsanity.com/paper/2304.07051/) (2023)
- [DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain](https://mlsanity.com/paper/2410.14980/) (2024)
- [The Third Monocular Depth Estimation Challenge](https://mlsanity.com/paper/2404.16831/) (2024)
- [NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion](https://mlsanity.com/paper/2311.07166/) (2023)
- [Scalable Autoregressive Monocular Depth Estimation](https://mlsanity.com/paper/2411.11361/) (2024)
- [CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration](https://mlsanity.com/paper/2603.12721/) (2026)
- [Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2212.05315/) (2022)
- [RSRD: A Road Surface Reconstruction Dataset and Benchmark for Safe and Comfortable Autonomous Driving](https://mlsanity.com/paper/2310.02262/) (2023)
- [Joint Depth Prediction and Semantic Segmentation with Multi-View SAM](https://mlsanity.com/paper/2311.00134/) (2023)

## Abstract (arXiv)

Monocular Depth Estimation (MDE) aims to predict pixel-wise depth given a single RGB image. For both, the convolutional as well as the recent attention-based models, encoder-decoder-based architectures have been found to be useful due to the simultaneous requirement of global context and pixel-level resolution. Typically, a skip connection module is used to fuse the encoder and decoder features, which comprises of feature map concatenation followed by a convolution operation. Inspired by the demonstrated benefits of attention in a multitude of computer vision problems, we propose an attention-based fusion of encoder and decoder features. We pose MDE as a pixel query refinement problem, where coarsest-level encoder features are used to initialize pixel-level queries, which are then refined to higher resolutions by the proposed Skip Attention Module (SAM). We formulate the prediction problem as ordinal regression over the bin centers that discretize the continuous depth range and introduce a Bin Center Predictor (BCP) module that predicts bins at the coarsest level using pixel queries. Apart from the benefit of image adaptive depth binning, the proposed design helps learn improved depth embedding in initial pixel queries via direct supervision from the ground truth. Extensive experiments on the two canonical datasets, NYUV2 and KITTI, show that our architecture outperforms the state-of-the-art by 5.3% and 3.9%, respectively, along with an improved generalization performance by 9.4% on the SUNRGBD dataset. Code is available at https://github.com/ashutosh1807/PixelFormer.git.