# ATGV-Net: Accurate Depth Super-Resolution

arXiv: https://arxiv.org/abs/1607.07988 · HTML: https://mlsanity.com/paper/1607.07988/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2016.

## Built on by (most cited first, 22 of 22)

- [Discrete Cosine Transform Network for Guided Depth Map Super-Resolution](https://mlsanity.com/paper/2104.06977/) (2021)
- [Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline](https://mlsanity.com/paper/2104.06174/) (2021)
- [BridgeNet: A Joint Learning Network of Depth Map Super-Resolution and Monocular Depth Estimation](https://mlsanity.com/paper/2107.12541/) (2021)
- [Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution](https://mlsanity.com/paper/2103.12955/) (2021)
- [Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution](https://mlsanity.com/paper/2303.08942/) (2023)
- [A Comprehensive Review of Deep Learning-based Single Image Super-resolution](https://mlsanity.com/paper/2102.09351/) (2021)
- [Guided Depth Map Super-resolution: A Survey](https://mlsanity.com/paper/2302.09598/) (2023)
- [High-resolution Depth Maps Imaging via Attention-based Hierarchical Multi-modal Fusion](https://mlsanity.com/paper/2104.01530/) (2021)
- [Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolution](https://mlsanity.com/paper/2306.00386/) (2023)
- [DuCos: Duality Constrained Depth Super-Resolution via Foundation Model](https://mlsanity.com/paper/2503.04171/) (2025)
- [RGB Guided ToF Imaging System: A Survey of Deep Learning-based Methods](https://mlsanity.com/paper/2405.10357/) (2024)
- [SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering](https://mlsanity.com/paper/2212.04968/) (2022)
- [Real-GDSR: Real-World Guided DSM Super-Resolution via Edge-Enhancing Residual Network](https://mlsanity.com/paper/2404.03930/) (2024)
- [StereoVAE: A lightweight stereo-matching system using embedded GPUs](https://mlsanity.com/paper/2305.11566/) (2023)
- [SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing](https://mlsanity.com/paper/2103.12981/) (2021)
- [Unpaired Depth Super-Resolution in the Wild](https://mlsanity.com/paper/2105.12038/) (2021)
- [AutoDepthNet: High Frame Rate Depth Map Reconstruction using Commodity Depth and RGB Cameras](https://mlsanity.com/paper/2305.14731/) (2023)
- [Learning Hierarchical Color Guidance for Depth Map Super-Resolution](https://mlsanity.com/paper/2403.07290/) (2024)
- [2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction](https://mlsanity.com/paper/2603.19964/) (2026)
- [Is Differentiable Architecture Search truly a One-Shot Method?](https://mlsanity.com/paper/2108.05647/) (2021)
- [IGAF: Incremental Guided Attention Fusion for Depth Super-Resolution](https://mlsanity.com/paper/2501.01723/) (2025)
- [Interactive State Space Model with Cross-Modal Local Scanning for Depth Super-Resolution](https://mlsanity.com/paper/2605.11934/) (2026)

## Abstract (arXiv)

In this work we present a novel approach for single depth map super-resolution. Modern consumer depth sensors, especially Time-of-Flight sensors, produce dense depth measurements, but are affected by noise and have a low lateral resolution. We propose a method that combines the benefits of recent advances in machine learning based single image super-resolution, i.e. deep convolutional networks, with a variational method to recover accurate high-resolution depth maps. In particular, we integrate a variational method that models the piecewise affine structures apparent in depth data via an anisotropic total generalized variation regularization term on top of a deep network. We call our method ATGV-Net and train it end-to-end by unrolling the optimization procedure of the variational method. To train deep networks, a large corpus of training data with accurate ground-truth is required. We demonstrate that it is feasible to train our method solely on synthetic data that we generate in large quantities for this task. Our evaluations show that we achieve state-of-the-art results on three different benchmarks, as well as on a challenging Time-of-Flight dataset, all without utilizing an additional intensity image as guidance.