# VoxDepth: Rectification of Depth Images on Edge Devices

arXiv: https://arxiv.org/abs/2407.15067 · HTML: https://mlsanity.com/paper/2407.15067/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 67 references that are in the map.
- First posted on arXiv 21 Jul 2024.

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [Deep Depth Completion of a Single RGB-D Image](https://mlsanity.com/paper/1803.09326/) (2018)
- [Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints](https://mlsanity.com/paper/1910.06727/) (2019)
- [FastDepth: Fast Monocular Depth Estimation on Embedded Systems](https://mlsanity.com/paper/1903.03273/) (2019)
- [Intel RealSense Stereoscopic Depth Cameras](https://mlsanity.com/paper/1705.05548/) (2017)
- [Learning Joint 2D-3D Representations for Depth Completion](https://mlsanity.com/paper/2012.12402/) (2020)
- [SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields](https://mlsanity.com/paper/2212.02501/) (2022)
- [Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries](https://mlsanity.com/paper/2104.02253/) (2021)
- [Depth image denoising using nuclear norm and learning graph model](https://mlsanity.com/paper/2008.03741/) (2020)
- [Self-Supervised Deep Depth Denoising](https://mlsanity.com/paper/1909.01193/) (2019)

## Abstract (arXiv)

Autonomous mobile robots like self-flying drones and industrial robots heavily depend on depth images to perform tasks such as 3D reconstruction and visual SLAM. However, the presence of inaccuracies in these depth images can greatly hinder the effectiveness of these applications, resulting in sub-optimal results. Depth images produced by commercially available cameras frequently exhibit noise, which manifests as flickering pixels and erroneous patches. ML-based methods to rectify these images are unsuitable for edge devices that have very limited computational resources. Non-ML methods are much faster but have limited accuracy, especially for correcting errors that are a result of occlusion and camera movement. We propose a scheme called VoxDepth that is fast, accurate, and runs very well on edge devices. It relies on a host of novel techniques: 3D point cloud construction and fusion, and using it to create a template that can fix erroneous depth images. VoxDepth shows superior results on both synthetic and real-world datasets. We demonstrate a 31% improvement in quality as compared to state-of-the-art methods on real-world depth datasets, while maintaining a competitive framerate of 27 FPS (frames per second).