This repository contains the code for "SBEVNet: End-to-End Deep Stereo Layout Estimation" paper by Divam Gupta, Wei Pu, Trenton Tabor, Jeff Schneider

Overview

SBEVNet: End-to-End Deep Stereo Layout Estimation

This repository contains the code for "SBEVNet: End-to-End Deep Stereo Layout Estimation" paper by Divam Gupta, Wei Pu, Trenton Tabor, Jeff Schneider

Usage

Dependencies

pip install --upgrade git+https://github.com/divamgupta/pytorch-propane
pip install torch==1.4.0 torchvision==0.5.0
pip install opencv-python
pip install torchgeometry

Dataset and Directories

For the example we use the following directories:

  • Datasets : ./datasets/carla/ and ./datasets/kitti/
  • Weights : ./sbevnet_weights/carla and ./sbevnet_weights/kitti
  • Predictions : ./predictions/kitti ./predictions/carla

Download and unzip the datasets and place them in ./datasets directory

Training

cd <cloned_repo_path>

Training the model on the CARLA dataset:

pytorch_propane sbevnet train    \
 --model_name sbevnet_model --network_name sbevnet --dataset_name  sbevnet_dataset_main --dataset_split train \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test \
 --batch_size 3  --eval_batch_size 1 \
 --n_epochs 20   --overwrite_epochs true  \
 --datapath "datasets/carla/dataset.json" \
 --save_path "sbevnet_weights/carla/carla_save_0" \
 --image_w 512 \
 --image_h 288 \
 --max_disp 64 \
 --n_hmap 100 \
 --xmin 1 \
 --xmax 39 \
 --ymin -19 \
 --ymax 19 \
 --cx 256 \
 --cy 144 \
 --f 179.2531 \
 --tx 0.2 \
 --camera_ext_x 0.9 \
 --camera_ext_y -0.1 \
 --fixed_cam_confs true \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true --check_degenerate true 

Training the model on the KITTI dataset:

pytorch_propane sbevnet train    \
 --model_name sbevnet_model --network_name sbevnet --dataset_name  sbevnet_dataset_main --dataset_split train \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test \
 --batch_size 3  --eval_batch_size 1 \
 --n_epochs 40   --overwrite_epochs true  \
 --datapath "datasets/kitti/dataset.json" \
 --save_path "sbevnet_weights/kitti/kitti_save_0" \
 --image_w 640 \
 --image_h 256 \
 --max_disp 64 \
 --n_hmap 128 \
 --xmin 5.72 \
 --xmax 43.73 \
 --ymin -19 \
 --ymax 19 \
 --camera_ext_x 0 \
 --camera_ext_y 0 \
 --fixed_cam_confs false \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true --check_degenerate true 

Evaluation

Evaluating the model on the CARLA dataset:

pytorch_propane sbevnet eval_iou    \
 --model_name sbevnet_model --network_name sbevnet \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test --dataset_type carla \
 --eval_batch_size 1 \
 --datapath "datasets/carla/dataset.json" \
 --load_checkpoint_path "sbevnet_weights/carla/carla_save_0" \
 --image_w 512 \
 --image_h 288 \
 --max_disp 64 \
 --n_hmap 100 \
 --xmin 1 \
 --xmax 39 \
 --ymin -19 \
 --ymax 19 \
 --cx 256 \
 --cy 144 \
 --f 179.2531 \
 --tx 0.2 \
 --camera_ext_x 0.9 \
 --camera_ext_y -0.1 \
 --fixed_cam_confs true \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true 

Evaluating the model on the KITTI dataset:

pytorch_propane sbevnet eval_iou    \
 --model_name sbevnet_model --network_name sbevnet  \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test --dataset_type kitti \
 --eval_batch_size 1 \
 --datapath "datasets/kitti/dataset.json" \
 --load_checkpoint_path "sbevnet_weights/kitti/kitti_save_0" \
 --image_w 640 \
 --image_h 256 \
 --max_disp 64 \
 --n_hmap 128 \
 --xmin 5.72 \
 --xmax 43.73 \
 --ymin -19 \
 --ymax 19 \
 --camera_ext_x 0 \
 --camera_ext_y 0 \
 --fixed_cam_confs false \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true 

Save Predictions

Save predictions of the model on the CARLA dataset:

pytorch_propane sbevnet save_preds    \
 --model_name sbevnet_model --network_name sbevnet \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test --output_dir "predictions/kitti" \
 --eval_batch_size 1 \
 --datapath "datasets/carla/dataset.json" \
 --load_checkpoint_path "sbevnet_weights/carla/carla_save_0" \
 --image_w 512 \
 --image_h 288 \
 --max_disp 64 \
 --n_hmap 100 \
 --xmin 1 \
 --xmax 39 \
 --ymin -19 \
 --ymax 19 \
 --cx 256 \
 --cy 144 \
 --f 179.2531 \
 --tx 0.2 \
 --camera_ext_x 0.9 \
 --camera_ext_y -0.1 \
 --fixed_cam_confs true \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true 

Save predictions of the model on the KITTI dataset:

pytorch_propane sbevnet save_preds    \
 --model_name sbevnet_model --network_name sbevnet  \
 --eval_dataset_name "sbevnet_dataset_main" --eval_dataset_split test --output_dir "predictions/kitti" \
 --eval_batch_size 1 \
 --datapath "datasets/kitti/dataset.json" \
 --load_checkpoint_path "sbevnet_weights/kitti/kitti_save_0" \
 --image_w 640 \
 --image_h 256 \
 --max_disp 64 \
 --n_hmap 128 \
 --xmin 5.72 \
 --xmax 43.73 \
 --ymin -19 \
 --ymax 19 \
 --camera_ext_x 0 \
 --camera_ext_y 0 \
 --fixed_cam_confs false \
 --do_ipm_rgb true \
 --do_ipm_feats true  \
 --do_mask true 
Owner
Divam Gupta
Graduate student at Carnegie Mellon University | Former Research Fellow at Microsoft Research
Divam Gupta
PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

Adam-NSCL This is a PyTorch implementation of Adam-NSCL algorithm for continual learning from our CVPR2021 (oral) paper: Title: Training Networks in N

Shipeng Wang 34 Dec 21, 2022
Object detection, 3D detection, and pose estimation using center point detection:

Objects as Points Object detection, 3D detection, and pose estimation using center point detection: Objects as Points, Xingyi Zhou, Dequan Wang, Phili

Xingyi Zhou 6.7k Jan 03, 2023
Machine learning framework for both deep learning and traditional algorithms

NeoML is an end-to-end machine learning framework that allows you to build, train, and deploy ML models. This framework is used by ABBYY engineers for

NeoML 704 Dec 27, 2022
ObjectDrawer-ToolBox: a graphical image annotation tool to generate ground plane masks for a 3D object reconstruction system

ObjectDrawer-ToolBox is a graphical image annotation tool to generate ground plane masks for a 3D object reconstruction system, Object Drawer.

77 Jan 05, 2023
Annealed Flow Transport Monte Carlo

Annealed Flow Transport Monte Carlo Open source implementation accompanying ICML 2021 paper by Michael Arbel*, Alexander G. D. G. Matthews* and Arnaud

DeepMind 30 Nov 21, 2022
minimizer-space de Bruijn graphs (mdBG) for whole genome assembly

rust-mdbg: Minimizer-space de Bruijn graphs (mdBG) for whole-genome assembly rust-mdbg is an ultra-fast minimizer-space de Bruijn graph (mdBG) impleme

Barış Ekim 148 Dec 01, 2022
This project aims to be a handler for input creation and running of multiple RICEWQ simulations.

What is autoRICEWQ? This project aims to be a handler for input creation and running of multiple RICEWQ simulations. What is RICEWQ? From the descript

Yass Fuentes 1 Feb 01, 2022
Self-supervised learning on Graph Representation Learning (node-level task)

graph_SSL Self-supervised learning on Graph Representation Learning (node-level task) How to run the code To run GRACE, sh run_GRACE.sh To run GCA, sh

Namkyeong Lee 3 Dec 31, 2021
Here is the implementation of our paper S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations.

S2VC Here is the implementation of our paper S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations. In thi

81 Dec 15, 2022
An NVDA add-on to split screen reader and audio from other programs to different sound channels

An NVDA add-on to split screen reader and audio from other programs to different sound channels (add-on idea credit: Tony Malykh)

Joseph Lee 7 Dec 25, 2022
HINet: Half Instance Normalization Network for Image Restoration

HINet: Half Instance Normalization Network for Image Restoration Liangyu Chen, Xin Lu, Jie Zhang, Xiaojie Chu, Chengpeng Chen Paper: https://arxiv.org

303 Dec 31, 2022
Code repository for Semantic Terrain Classification for Off-Road Autonomous Driving

BEVNet Datasets Datasets should be put inside data/. For example, data/semantic_kitti_4class_100x100. Training BEVNet-S Example: cd experiments bash t

(Brian) JoonHo Lee 24 Dec 12, 2022
Python package facilitating the use of Bayesian Deep Learning methods with Variational Inference for PyTorch

PyVarInf PyVarInf provides facilities to easily train your PyTorch neural network models using variational inference. Bayesian Deep Learning with Vari

342 Dec 02, 2022
Code for paper: "Spinning Language Models for Propaganda-As-A-Service"

Spinning Language Models for Propaganda-As-A-Service This is the source code for the Arxiv version of the paper. You can use this Google Colab to expl

Eugene Bagdasaryan 16 Jan 03, 2023
An Inverse Kinematics library aiming performance and modularity

IKPy Demo Live demos of what IKPy can do (click on the image below to see the video): Also, a presentation of IKPy: Presentation. Features With IKPy,

Pierre Manceron 481 Jan 02, 2023
A minimal TPU compatible Jax implementation of NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

NeRF Minimal Jax implementation of NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. Result of Tiny-NeRF RGB Depth

Soumik Rakshit 11 Jul 24, 2022
Deep learning PyTorch library for time series forecasting, classification, and anomaly detection

Deep learning for time series forecasting Flow forecast is an open-source deep learning for time series forecasting framework. It provides all the lat

AIStream 1.2k Jan 04, 2023
This is the dataset for testing the robustness of various VO/VIO methods

KAIST VIO dataset This is the dataset for testing the robustness of various VO/VIO methods You can download the whole dataset on KAIST VIO dataset Ind

1 Sep 01, 2022
Implementation of Continuous Sparsification, a method for pruning and ticket search in deep networks

Continuous Sparsification Implementation of Continuous Sparsification (CS), a method based on l_0 regularization to find sparse neural networks, propo

Pedro Savarese 23 Dec 07, 2022
Pytorch implementation of MixNMatch

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation [Paper] Yuheng Li, Krishna Kumar Singh, Utkarsh Ojha, Yong Jae Le

910 Dec 30, 2022