Sync2Gen Code for ICCV 2021 paper: Scene Synthesis via Uncertainty-Driven Attribute Synchronization

Last update: Dec 30, 2022

Related tags

Deep Learning Sync2Gen

Overview

Sync2Gen

Code for ICCV 2021 paper: Scene Synthesis via Uncertainty-Driven Attribute Synchronization

0. Environment

Environment: python 3.6 and cuda 10.0 on Ubuntu 18.04

Pytorch 1.4.0
tensorflow 1.14.0 (for tensorboard)

1. Dataset

├──dataset_3dfront/
    ├──data
        ├── bedroom
            ├── 0_abs.npy
            ├── 0_rel.pkl
            ├── ...
        ├── living
            ├── 0_abs.npy
            ├── 0_rel.pkl
            ├── ...
        ├── train_bedroom.txt
        ├── train_living.txt
        ├── val_bedroom.txt
        └── val_living.txt

See 3D-FRONT Dataset for dataset generation.

2. VAE

2.1 Generate scenes from random noises

Download the pretrained model from https://drive.google.com/file/d/1VKNlEdUj1RBUOjBaBxE5xQvfsZodVjam/view?usp=sharing

Sync2Gen
└── log
    └── 3dfront
        ├── bedroom
        │   └── vaef_lr0001_w00001_B64
        │       ├── checkpoint_eval799.tar
        │       └── pairs
        └── living
            └── vaef_lr0001_w00001_B64
                ├── checkpoint_eval799.tar
                └── pairs

type='bedroom'; # or living
CUDA_VISIBLE_DEVICES=0 python ./test_sparse.py  --type $type  --log_dir ./log/3dfront/$type/vaef_lr0001_w00001_B64 --model_dict=model_scene_forward --max_parts=80 --num_class=20 --num_each_class=4 --batch_size=32 --variational --latent_dim 20 --abs_dim 16  --weight_kld 0.0001  --learning_rate 0.001 --use_dumped_pairs --dump_results --gen_from_noise --num_gen_from_noise 100

The predictions are dumped in ./dump/$type/vaef_lr0001_w00001_B64

2.2 Training

To train the network:

type='bedroom'; # or living
CUDA_VISIBLE_DEVICES=0 python ./train_sparse.py --data_path ./dataset_3dfront/data  --type $type  --log_dir ./log/3dfront/$type/vaef_lr0001_w00001_B64  --model_dict=model_scene_forward --max_parts=80 --num_class=20 --num_each_class=4 --batch_size=64 --variational --latent_dim 20 --abs_dim 16  --weight_kld 0.0001  --learning_rate 0.001

3. Bayesian optimization

cd optimization

3.1 Prior generation

See Prior generation.

3.2 Optimization

type=bedroom # or living;
bash opt.sh $type vaef_lr0001_w00001_B64  EXP_NAME

We use Pytorch-LBFGS for optimization.

3.3 Visualization

There is a simple visualization tool:

type=bedroom # or living
bash vis.sh $type vaef_lr0001_w00001_B64 EXP_NAME

The visualization is in ./vis. {i:04d}_2(3)d_pred.png is the initial prediction from VAE. {i:04d}_2(3)d_sync.png is the optimized layout after synchronization.

Acknowledgements

The repo is built based on:

We thank the authors for their great job.

Contact

If you have any questions, you can contact Haitao Yang (yanghtr [AT] outlook [DOT] com).

Sync2Gen Code for ICCV 2021 paper: Scene Synthesis via Uncertainty-Driven Attribute Synchronization

Related tags

Overview

Sync2Gen

0. Environment

1. Dataset

2. VAE

2.1 Generate scenes from random noises

2.2 Training

3. Bayesian optimization

3.1 Prior generation

3.2 Optimization

3.3 Visualization

Acknowledgements

Contact

Owner

Haitao Yang

Implementation of the method described in the Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

Multi-modal Vision Transformers Excel at Class-agnostic Object Detection

This project is used for the paper Differentiable Programming of Isometric Tensor Network

ComPhy: Compositional Physical Reasoning ofObjects and Events from Videos

A knowledge base construction engine for richly formatted data

Implementation of ICCV19 Paper "Learning Two-View Correspondences and Geometry Using Order-Aware Network"

HAR-stacked-residual-bidir-LSTMs - Deep stacked residual bidirectional LSTMs for HAR

An energy estimator for eyeriss-like DNN hardware accelerator

Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection, AAAI 2021.

An executor that loads ONNX models and embeds documents using the ONNX runtime.

People movement type classifier with YOLOv4 detection and SORT tracking.

This is the codebase for the ICLR 2021 paper Trajectory Prediction using Equivariant Continuous Convolution

Pytorch implementation of "ARM: Any-Time Super-Resolution Method"

Evolution Strategies in PyTorch

Semi-supervised Semantic Segmentation with Directional Context-aware Consistency (CVPR 2021)

Recognize Handwritten Digits using Deep Learning on the browser itself.

PyTorch Implementation of Google Brain's WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis

Implementation for paper LadderNet: Multi-path networks based on U-Net for medical image segmentation

Official repository for: Continuous Control With Ensemble DeepDeterministic Policy Gradients

Cl datasets - PyTorch image dataloaders and utility functions to load datasets for supervised continual learning