Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Current state of supervised and unsupervised depth completion methods
| Date | Stars |
|---|---|
| 2026-07-24 | 515 |
| 2026-07-25 | 515 |
| 2026-07-28 | 515 |
| 2026-07-30 | 515 |
| 2026-08-06 | 515 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome Depth Completion
**Table of Contents**
- [About Sparse-to-Dense Depth Completion](#unsupervised-void-benchmark)
- [Current State of Depth Completion](#current-state-of-depth-completion)
- [Unsupervised VOID Benchmark](#unsupervised-void-benchmark)
- [Supervised VOID Benchmark](#supervised-void-benchmark)
- [Unsupervised KITTI Benchmark](#unsupervised-kitti-benchmark)
- [Supervised KITTI Benchmark](#supervised-kitti-benchmark)
## About Sparse-to-Dense Depth Completion <a name="about-sparse-to-dense-depth-completion"></a>
In the sparse-to-dense depth completion problem, one wants to infer the dense depth map of a 3-D scene given an RGB image and its corresponding sparse reconstruction in the form of a sparse depth map obtained either from computational methods such as SfM (Strcuture-from-Motion) or active sensors such as lidar or structured light sensors.
**Example 1: [VOID dataset](https://github.com/alexklwong/void-dataset) (indoor VIO)**
| *Input RGB image* | *Sparse point cloud*| *Output point cloud from [KBNet](https://github.com/alexklwong/calibrated-backprojection-network)* |
| :----------------------------------------- | :----------------------------------------- | :--------------------------------------------------------: |
| <img src="figures/void_teaser_image_306.png" width="200"> | <img src="figures/void_teaser_sparse_point_cloud_306.gif" width="200"> | <img src="figures/void_teaser_kbnet_output_306.gif" width="200"> |
**Example 2: [KITTI dataset](http://www.cvlibs.net/datasets/kitti/) (outdoor lidar)**
| *Input RGB image* | *Output point cloud from [ScaffNet](https://github.com/alexklwong/learning-topology-synthetic-data)* |
| :------------------------------------------ | :--------------------------------------------------------: |
| <img src="figures/kitti_teaser_image.png" width="400"> | <img src="figures/kitti_teaser_scaffnet_output.gif" width="400"> |
## Current State of Depth Completion Methods <a name="current-state-of-depth-completion"></a>
Here we compile both unsupervised/self-supervised (monocular and stereo) and supervised methods published in recent conferences and journals on the VOID (Wong et. al., 2020) and KITTI (Uhrig et. al., 2017) depth completion benchmarks. Our ranking considers all four metrics rather than just RMSE.
**Quick Links**
- [Unsupervised VOID Benchmark](#unsupervised-void-benchmark)
- [Supervised VOID Benchmark](#supervised-void-benchmark)
- [Unsupervised KITTI Benchmark](#unsupervised-kitti-benchmark)
- [Supervised KITTI Benchmark](#supervised-kitti-benchmark)
### Unsupervised VOID Depth Completion Benchmark <a name="unsupervised-void-benchmark"></a>
| Paper | Publication | Code | MAE | RMSE | iMAE | iRMSE |
| :---- | :---------: | :--: | :-: | :--: | :--: | ----: |
| AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation | [ECCV 2024](https://arxiv.org/pdf/2310.09739) | [PyTorch](https://github.com/alexklwong/augundo) | **33.32** | **85.67** | **16.61** | **41.24** |
| Monitored Distillation for Positive Congruent Depth Completion| [ECCV 2022](https://arxiv.org/pdf/2203.16034.pdf) | [PyTorch](https://github.com/alexklwong/mondi-python) | 36.42 | 87.78 | 19.18 | 43.83 |
| DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion | [AAAI 2023](https://arxiv.org/pdf/2211.10994) | N/A | 37.41 | 93.31 | 19.17 | 45.57 |
| Unsupervised Depth Completion with Calibrated Backprojection Layers| [ICCV 2021](https://arxiv.org/pdf/2108.10531.pdf) | [PyTorch](https://github.com/alexklwong/calibrated-backprojection-network) | 39.80 | 95.86 | 21.16 | 49.72 |
| Learning Topology from Synthetic Data for Unsupervised Depth Completion | [RA-L & ICRA 2021](https://arxiv.org/pdf/2106.02994.pdf) | [TensorFlow/PyTorch](https://github.com/alexklwong/learning-topology-synthetic-data) | 60.68 | 122.01 | 35.24 | 67.34 |
| Unsupervised Depth Completion from Visual Inertial Odometry | [RA-L & ICRA 2020](https://arxiv.org/Excerpt of 18,819 characters
Read on GitHub
17
5
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0ad726e79a87fecf, topic:computer-vision, topic:3d-reconstruction
matched fp:0ad726e79a87fecf, topic:benchmark
matched fp:0ad726e79a87fecf, topic:awesome