• Stars
    star
    161
  • Rank 233,470 (Top 5 %)
  • Language
    Python
  • License
    MIT License
  • Created over 4 years ago
  • Updated about 3 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Official PyTorch implementation of CVPR 2020 oral "Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors"

Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors

Official PyTorch implementation of the CVPR 2020 paper "Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors" by the ML Team at Toyota Research Institute (TRI), cf. References below. [Full paper] [YouTube]

Setting up your environment

To set up the environment using conda, use the following commands:

conda env create -n sdflabel -f environment.yml
conda activate sdflabel

Add the sdfrenderer directory to PYTHONPATH:

export PYTHONPATH="${PYTHONPATH}:/path/to/sdfrenderer"

Optimization demo

To run the optimization demo, first download the data folder. Then, extract the archive to the root folder of the project and run the following command:

python main.py configs/config_refine.ini --demo

Training CSS network

To train the CSS network, run the following command:

python main.py configs/config_train.ini --train

Dataset format

The dataset of crops represents a collection of detected RGB patches (CSS input), corresponding NOCS patches (CSS output), and a JSON DB file comprising the patch relevant information (most importantly SDF latent vectors corresponding to the depicted 3D models). An example of such dataset is located in the data/db/crops folder.

Optimization

Download KITTI 3D and modify the kitti_path in the config file config_refine.ini accordingly. To run optimization on the KITTI 3D dataset, run the following command:

python main.py configs/config_refine.ini --refine

Upon completion, autolabels will be stored to the output folder specified in the config file (output -> labels). To evaluate the generated dump, run:

python main.py configs/config_refine.ini --evaluate

License

The source code is released under the MIT license.

References

Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors (CVPR 2020 oral)

Sergey Zakharov*, Wadim Kehl*, Arjun Bhargava, Adrien Gaidon

@inproceedings{sdflabel,
author = {Sergey Zakharov and Wadim Kehl and Arjun Bhargava and Adrien Gaidon},
title = {Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors},
booktitle = {IEEE Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

More Repositories

1

packnet-sfm

TRI-ML Monocular Depth Estimation Repository
Python
1,243
star
2

vidar

Python
560
star
3

DDAD

Dense Depth for Autonomous Driving (DDAD) dataset.
Python
490
star
4

dd3d

Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park*, Rares Ambrus*, Vitor Guizilini, Jie Li, and Adrien Gaidon.
Python
464
star
5

prismatic-vlms

A flexible and efficient codebase for training visually-conditioned language models (VLMs)
Python
445
star
6

KP3D

Code for "Self-Supervised 3D Keypoint Learning for Ego-motion Estimation"
Python
240
star
7

PF-Track

Implementation of PF-Track
Python
203
star
8

KP2D

Python
176
star
9

realtime_panoptic

Official PyTorch implementation of CVPR 2020 Oral: Real-Time Panoptic Segmentation from Dense Detections
Python
115
star
10

permatrack

Implementation for Learning to Track with Object Permanence
Python
112
star
11

camviz

Visualization Library
Python
101
star
12

dgp

ML Dataset Governance Policy for Autonomous Vehicle Datasets
Python
94
star
13

VEDet

Python
39
star
14

RAP

This is the official code for the paper RAP: Risk-Aware Prediction for Robust Planning: https://arxiv.org/abs/2210.01368
Python
34
star
15

VOST

Code for the VOST dataset
Python
22
star
16

RAM

Implementation for Object Permanence Emerges in a Random Walk along Memory
Python
18
star
17

road

ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapes (CoRL 2022)
Python
11
star
18

efm_datasets

TRI-ML Embodied Foundation Datasets
Python
8
star
19

OctMAE

Zero-Shot Multi-Object Shape Completion (ECCV 2024)
Python
5
star
20

refine

Official PyTorch implementation of the SIGGRAPH 2024 paper "ReFiNe: Recursive Field Networks for Cross-Modal Multi-Scene Representation"
Python
5
star
21

stochastic_verification

Official repository for the paper "How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation"
Python
5
star
22

HAICU

4
star
23

binomial_cis

Computation of binomial confidence intervals that achieve exact coverage.
Jupyter Notebook
4
star
24

vlm-evaluation

VLM Evaluation: Benchmark for VLMs, spanning text generation tasks from VQA to Captioning
Python
1
star