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.
ICRA 2018 "Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image" (Torch Implementation)
| Date | Stars |
|---|---|
| 2026-07-24 | 444 |
| 2026-07-25 | 445 |
| 2026-07-28 | 445 |
| 2026-07-30 | 445 |
| 2026-08-06 | 445 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
Sparse-to-Dense ============================ This repo implements the training and testing of deep regression neural networks for ["Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image"](https://arxiv.org/pdf/1709.07492.pdf) by [Fangchang Ma](http://www.mit.edu/~fcma) and [Sertac Karaman](http://karaman.mit.edu/) at MIT. A video demonstration is available on [YouTube](https://youtu.be/vNIIT_M7x7Y). This repo offers the original implementation of the paper in [Torch](http://torch.ch/docs/getting-started.html). The [PyTorch](http://pytorch.org/) version can be found [here](https://github.com/fangchangma/sparse-to-dense.pytorch). <p align="center"> <img src="http://www.mit.edu/~fcma/images/ICRA2018.png" alt="photo not available" width="50%" height="50%"> <img src="https://j.gifs.com/Z4qDow.gif" alt="photo not available" height="50%"> </p> This repo can be used for training and testing of - RGB (or grayscale image) based depth prediction - sparse depth based depth prediction - RGBd (i.e., both RGB and sparse depth) based depth prediction ## Contents 0. [Requirements](#requirements) 0. [Training](#training) 0. [Testing](#testing) 0. [Trained Models](#trained-models) 0. [Benchmark](#benchmark) 0. [Citation](#citation) ## Requirements See the [installation instructions](INSTALL.md) for a step-by-step guide. - Install [Torch](http://torch.ch/docs/getting-started.html) on a machine with CUDA GPU. - Install [cuDNN](https://developer.nvidia.com/cudnn)(v4 or above) and the Torch [cuDNN bindings](https://github.com/soumith/cudnn.torch/tree/R4) - If you already have both Torch and cuDNN installed, update packages and install dependencies. ```bash luarocks install nn luarocks install cunn luarocks install cudnn luarocks install optnet ``` - Install the [HDF5](https://en.wikipedia.org/wiki/Hierarchical_Data_Format) format libraries. Files in our pre-processed datasets are in HDF5 formats. ```bash sudo apt-get update sudo apt-get install -y libhdf5-serial-dev hdf5-tools git clone https://github.com/davek44/torch-hdf5.git cd torch-hdf5 luarocks make cd .. ``` - Download the preprocessed [NYU Depth V2](http://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html) and/or [KITTI](http://www.cvlibs.net/datasets/kitti/eval_odometry.php) datasets in HDF5 formats and place them under the `data` folder. The downloading process might take an hour or so. The NYU dataset requires 32G of storage space, and KITTI requires 81G. ```bash cd data wget http://datasets.lids.mit.edu/sparse-to-dense/data/kitti.tar.gz tar -xvf kitti.tar.gz && rm -f kitti.tar.gz wget http://datasets.lids.mit.edu/sparse-to-dense/data/nyudepthv2.tar.gz tar -xvf nyudepthv2.tar.gz && rm -f nyudepthv2.tar.gz cd .. ``` - Download the networks pretrained on ImageNet datasets. In particular, use [ResNet-50](https://d2j0dndfm35trm.cloudfront.net/resnet-50.t7) for the NYU Depth V2 dataset, and [ResNet-18](https://d2j0dndfm35trm.cloudfront.net/resnet-18.t7) for the KITTI dataset. Place them under the `pretrained` folder. ```bash cd pretrained wget https://d2j0dndfm35trm.cloudfront.net/resnet-50.t7 wget https://d2j0dndfm35trm.cloudfront.net/resnet-18.t7 cd .. ``` ## Training The training scripts come with several options, which can be listed with the `--help` flag. ```bash th main.lua --help ``` To run the training, simply run main.lua. By default, the script runs the RGB-based prediction network on NYU-Depth-V2 with 1 GPU and 2 data-loader threads without using pretrained weights. ```bash th main.lua ``` To train networks with different datasets, input modalities, loss functions, and components, see the example below: ```bash th main.lua -dataset kitti -inputType rgbd -nSample 100 -criterion l1 -encoderType conv -decoderType upproj -pretrain true ``` Training results will be saved under the `results` folder. #### Model Options | Parameter | Options | Remarks | | ------------- | ----------- | ----------- | | d
Excerpt of 8,708 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1cbcb7da29890031, topic:deep-learning
matched fp:1cbcb7da29890031, topic:computer-vision