# Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries

arXiv: https://arxiv.org/abs/1803.08673 · HTML: https://mlsanity.com/paper/1803.08673/

## Key facts

- Cited by 145 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2018.

## Built on by (most cited first, 30 of 145)

- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image](https://mlsanity.com/paper/2403.12013/) (2024)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing](https://mlsanity.com/paper/2403.17822/) (2024)
- [DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation](https://mlsanity.com/paper/2203.14211/) (2022)
- [TransformerFusion: Monocular RGB Scene Reconstruction using Transformers](https://mlsanity.com/paper/2107.02191/) (2021)
- [LocalBins: Improving Depth Estimation by Learning Local Distributions](https://mlsanity.com/paper/2203.15132/) (2022)
- [Balanced MSE for Imbalanced Visual Regression](https://mlsanity.com/paper/2203.16427/) (2022)
- [SimpleRecon: 3D Reconstruction Without 3D Convolutions](https://mlsanity.com/paper/2208.14743/) (2022)
- [Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis](https://mlsanity.com/paper/2505.09358/) (2025)
- [Panoptic 3D Scene Reconstruction From a Single RGB Image](https://mlsanity.com/paper/2111.02444/) (2021)
- [ROCA: Robust CAD Model Retrieval and Alignment from a Single Image](https://mlsanity.com/paper/2112.01988/) (2021)
- [Pri3D: Can 3D Priors Help 2D Representation Learning?](https://mlsanity.com/paper/2104.11225/) (2021)
- [NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation](https://mlsanity.com/paper/2203.04802/) (2022)
- [VA-DepthNet: A Variational Approach to Single Image Depth Prediction](https://mlsanity.com/paper/2302.06556/) (2023)
- [Source-free Depth for Object Pop-out](https://mlsanity.com/paper/2212.05370/) (2022)
- [Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction](https://mlsanity.com/paper/2103.04216/) (2021)
- [TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations](https://mlsanity.com/paper/2103.15982/) (2021)
- [Adaptive Surface Normal Constraint for Depth Estimation](https://mlsanity.com/paper/2103.15483/) (2021)
- [Toward Practical Monocular Indoor Depth Estimation](https://mlsanity.com/paper/2112.02306/) (2021)
- [Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries](https://mlsanity.com/paper/2104.02253/) (2021)
- [Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks](https://mlsanity.com/paper/2303.15710/) (2023)
- [Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objects](https://mlsanity.com/paper/2110.00087/) (2021)
- [Pano3D: A Holistic Benchmark and a Solid Baseline for 360o Depth Estimation](https://mlsanity.com/paper/2109.02749/) (2021)
- [StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation](https://mlsanity.com/paper/2108.08574/) (2021)
- [RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2207.11984/) (2022)
- [Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN](https://mlsanity.com/paper/2308.08333/) (2023)
- [Deep Depth Completion from Extremely Sparse Data: A Survey](https://mlsanity.com/paper/2205.05335/) (2022)
- [M3D-VTON: A Monocular-to-3D Virtual Try-On Network](https://mlsanity.com/paper/2108.05126/) (2021)
- [Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2203.02112/) (2022)

## Abstract (arXiv)

This paper considers the problem of single image depth estimation. The employment of convolutional neural networks (CNNs) has recently brought about significant advancements in the research of this problem. However, most existing methods suffer from loss of spatial resolution in the estimated depth maps; a typical symptom is distorted and blurry reconstruction of object boundaries. In this paper, toward more accurate estimation with a focus on depth maps with higher spatial resolution, we propose two improvements to existing approaches. One is about the strategy of fusing features extracted at different scales, for which we propose an improved network architecture consisting of four modules: an encoder, decoder, multi-scale feature fusion module, and refinement module. The other is about loss functions for measuring inference errors used in training. We show that three loss terms, which measure errors in depth, gradients and surface normals, respectively, contribute to improvement of accuracy in an complementary fashion. Experimental results show that these two improvements enable to attain higher accuracy than the current state-of-the-arts, which is given by finer resolution reconstruction, for example, with small objects and object boundaries.