# Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Composition

arXiv: https://arxiv.org/abs/2212.01538 · HTML: https://mlsanity.com/paper/2212.01538/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 39 references that are in the map.
- First posted on arXiv 3 Dec 2022.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Learning to Recover 3D Scene Shape from a Single Image](https://mlsanity.com/paper/2012.09365/) (2020)
- [Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields](https://mlsanity.com/paper/1502.07411/) (2015)
- [Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos](https://mlsanity.com/paper/1811.06152/) (2018)
- [3D Ken Burns Effect from a Single Image](https://mlsanity.com/paper/1909.05483/) (2019)
- [Semi-Supervised Deep Learning for Monocular Depth Map Prediction](https://mlsanity.com/paper/1702.02706/) (2017)
- [Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging](https://mlsanity.com/paper/2105.14021/) (2021)
- [SCORES: Shape Composition with Recursive Substructure Priors](https://mlsanity.com/paper/1809.05398/) (2018)
- [On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach](https://mlsanity.com/paper/1803.09719/) (2018)
- [Stereo Matching by Self-supervision of Multiscopic Vision](https://mlsanity.com/paper/2104.04170/) (2021)
- [SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1906.08889/) (2019)

## Built on by (most cited first, 8 of 8)

- [Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2212.05315/) (2022)
- [Self-Distilled Depth Refinement with Noisy Poisson Fusion](https://mlsanity.com/paper/2409.17880/) (2024)
- [The Devil is in the Edges: Monocular Depth Estimation with Edge-aware Consistency Fusion](https://mlsanity.com/paper/2404.00373/) (2024)
- [One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Images](https://mlsanity.com/paper/2503.22351/) (2025)
- [Any Resolution Any Geometry: From Multi-View To Multi-Patch](https://mlsanity.com/paper/2603.03026/) (2026)
- [DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selection](https://mlsanity.com/paper/2605.23281/) (2026)
- [SUPER Module for Detail-Sensitive and Cost-Efficient U-Net Variant Decoders](https://mlsanity.com/paper/2511.11015/) (2025)
- [Bayesian Monocular Depth Refinement via Neural Radiance Fields](https://mlsanity.com/paper/2601.03869/) (2026)

## Abstract (arXiv)

Monocular depth estimation is a challenging problem on which deep neural networks have demonstrated great potential. However, depth maps predicted by existing deep models usually lack fine-grained details due to the convolution operations and the down-samplings in networks. We find that increasing input resolution is helpful to preserve more local details while the estimation at low resolution is more accurate globally. Therefore, we propose a novel depth map fusion module to combine the advantages of estimations with multi-resolution inputs. Instead of merging the low- and high-resolution estimations equally, we adopt the core idea of Poisson fusion, trying to implant the gradient domain of high-resolution depth into the low-resolution depth. While classic Poisson fusion requires a fusion mask as supervision, we propose a self-supervised framework based on guided image filtering. We demonstrate that this gradient-based composition performs much better at noisy immunity, compared with the state-of-the-art depth map fusion method. Our lightweight depth fusion is one-shot and runs in real-time, making our method 80X faster than a state-of-the-art depth fusion method. Quantitative evaluations demonstrate that the proposed method can be integrated into many fully convolutional monocular depth estimation backbones with a significant performance boost, leading to state-of-the-art results of detail enhancement on depth maps.