• Stars
    star
    113
  • Rank 302,869 (Top 7 %)
  • Language
    Python
  • License
    MIT License
  • Created over 4 years ago
  • Updated about 4 years ago

Reviews

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

Repository Details

This repository contains code for the paper 'Texture Fields: Learning Texture Representations in Function Space'.

Texture Fields

This repository contains code for the paper 'Texture Fields: Learning Texture Representations in Function Space'.

You can find detailed usage instructions for training your own models and using pretrained models below.

If you find our code or paper useful, please consider citing

@inproceedings{OechsleICCV2019,
    title = {Texture Fields: Learning Texture Representations in Function Space},
    author = {Oechsle, Michael and Mescheder,Lars and Niemeyer, Michael and Strauss, Thilo and Geiger, Andreas},
    booktitle = {Proceedings IEEE International Conf. on Computer Vision (ICCV)},
    year = {2019}
}

Installation

The simplest way to run our implementation is to use anaconda.

You can create an anaconda environment called texturefields with

conda env create -f environment.yaml
conda activate texturefields

Demo

If you just want to quickly test our method on the single view reconstruction task, you can run our demo with

python generate.py configs/singleview/texfields/car_demo.yaml 

The script is using a pre-trained model for reconstructing the texture of the car object provided in data/demo/. You can find predicted images in out/demo/fake/.

Dataset

For downloading the preprocessed data, run the following script.

source ./scripts/download_data.sh

We just provide data for the car category with a file size of 33 GB. The dataset is copied to the data/ folder. For each 3D object we have 17 input views, 10 random views with corresponding depth maps and camera information. The train, test and validation splits are located in the main sub folder of the categories. For visualization, we provide renderings from fixed views in th visualize subfolder. Data structure:


data/shapenet/data_cars/{ModelID}/
     input_image/
     image/
     depth/
     visualize/
         image/
         depth/
     pointcloud.npz


Usage

You can use our implementation for training, generation and evaluation. For each mode there is a corresponding file that needs to be run.

Generation

Single View Texture Reconstruction

For testing our method, you can generate novel views by running

python generate.py CONFIG.yaml

CONFIG.yaml stands for the path to a config file. For generation, you can choose whether the views are from random views or fixed views on a circle around the object. If you would like to use random views you can add to the config file

test:
  dataset_split: 'test_eval' 

to the config file. For evaluating fixed views, you can replace the option with 'test_vis'. For the evaluation we use the random views. Example of config files can be found in

configs/singleview/car.yaml
configs/singleview/car_eval_rnd.yaml

Generative Model

You can run our generative models by executing

python generate.py configs/VAE/000_eval_fix.yaml

for the GAN

python generate.py configs/GAN/000_eval_fix.yaml

for predicting novel texture in

out/VAE/car/eval_fix/
out/GAN/car/eval_fix/

Evaluation

You can evaluate the performance of our method on the single view reconstruction task by running

python generate.py configs/singleview/car_eval_rnd.yaml
python evaluate.py configs/singleview/car_eval_rnd.yaml

The script writes the results into the respective output folder.

out/singleview/car/eval_rnd/

Training

For training a model from scratch run

python train.py CONFIG.yaml

in the conda environement. Please set the following option in the config file:

model:
  model_url:

So that pre-trained model are not loaded. The training process can be visualized with tensorboard. The logfiles are saved to the logs folder in the output directory.

tensorboard --logdir ./out --port 6006

More Repositories

1

sdfstudio

A Unified Framework for Surface Reconstruction
Python
1,861
star
2

occupancy_networks

This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"
Python
1,454
star
3

giraffe

This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"
Python
1,227
star
4

stylegan-t

[ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
Python
1,122
star
5

transfuser

[PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving; [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving
Python
957
star
6

stylegan-xl

[SIGGRAPH'22] StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
Python
939
star
7

projected-gan

[NeurIPS'21] Projected GANs Converge Faster
Python
876
star
8

unimatch

[TPAMI'23] Unifying Flow, Stereo and Depth Estimation
Python
855
star
9

convolutional_occupancy_networks

[ECCV'20] Convolutional Occupancy Networks
Python
792
star
10

differentiable_volumetric_rendering

This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"
Python
782
star
11

mip-splatting

[CVPR'24 Oral] Mip-Splatting: Alias-free 3D Gaussian Splatting
Python
700
star
12

monosdf

[NeurIPS'22] MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction
Python
535
star
13

shape_as_points

[NeurIPS'21] Shape As Points: A Differentiable Poisson Solver
Python
518
star
14

unisurf

[ICCV'21] UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction
Python
410
star
15

graf

Official code release for "GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis"
Jupyter Notebook
393
star
16

tuplan_garage

[CoRL'23] Parting with Misconceptions about Learning-based Vehicle Motion Planning
Python
370
star
17

kitti360Scripts

This repository contains utility scripts for the KITTI-360 dataset.
Python
353
star
18

neat

[ICCV'21] NEAT: Neural Attention Fields for End-to-End Autonomous Driving
Python
301
star
19

gaussian-opacity-fields

Gaussian Opacity Fields for Efficient and Compact Surface Reconstruction in Unbounded Scenes
Python
285
star
20

occupancy_flow

This repository contains the code for the ICCV 2019 paper "Occupancy Flow - 4D Reconstruction by Learning Particle Dynamics"
Python
207
star
21

plant

[CoRL'22] PlanT: Explainable Planning Transformers via Object-Level Representations
Python
192
star
22

factor-fields

[SIGGRAPH 2023] We provide a unified formula for neural fields (Factor Fields) and a novel dictionary factorization (Dictionary Fields)
Jupyter Notebook
183
star
23

voxgraf

Official code release for VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
Python
123
star
24

carla_garage

[ICCV'23] Hidden Biases of End-to-End Driving Models
Python
121
star
25

sledge

SLEDGE: Synthesizing Simulation Environments for Driving Agents with Generative Models
105
star
26

kitti360LabelTool

JavaScript
103
star
27

counterfactual_generative_networks

[ICLR'21] Counterfactual Generative Networks
Python
102
star
28

gta

[ICLR'24] GTA: A Geometry-Aware Attention Mechanism for Multi-view Transformers
Python
95
star
29

murf

[CVPR'24] MuRF: Multi-Baseline Radiance Fields
Python
84
star
30

controllable_image_synthesis

Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis, CVPR 2020
Python
69
star
31

king

[ECCV'22] KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients
Python
61
star
32

handheld_svbrdf_geometry

On Joint Estimation of Pose, Geometry and svBRDF from a Handheld Scanner, CVPR2020
Python
57
star
33

navsim

NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation
Python
52
star
34

connecting_the_dots

This repository contains the code for the paper "Connecting the Dots: Learning Representations for Active Monocular Depth Estimation" https://avg.is.tuebingen.mpg.de/publications/riegler2019cvpr
Python
51
star
35

frequency_bias

Official code for "On the Frequency Bias of Generative Models", NeurIPS 2021
Python
39
star
36

data_aggregation

This repository contains the code for the CVPR 2020 paper "Exploring Data Aggregation in Policy Learning for Vision-based Urban Autonomous Driving"
Python
38
star
37

good

[ICLR'23] GOOD: Exploring Geometric Cues for Detecting Objects in an Open World
Python
36
star
38

campari

[3DV'21] CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields
Python
29
star
39

autonomousvision.github.io

Blog of the Autonomous Vision Group at MPI-IS Tübingen and University of Tübingen.
HTML
19
star
40

visual_abstractions

6
star
41

slides

Slide repository of the Autonomous Vision Group at MPI-IS Tübingen and University of Tübingen.
CSS
2
star
42

similarity_reconstruction

This code is based on the paper Exploiting Object Similarity in 3D Reconstruction.
C++
1
star
43

slow_flow

This code is based on the paper Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data.
C++
1
star