3D-RETR: End-to-End Single and Multi-View3D Reconstruction with Transformers

Last update: Dec 21, 2022

Related tags

Pytorch Utilities 3D-RETR

Overview

3D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformers (BMVC 2021)

Zai Shi, Zhao Meng, Yiran Xing, Yunpu Ma, Roger Wattenhofer

∗The first two authors contribute equally to this work

[BMVC (with presentation)] [Paper] [Supplementary]

Citation

@inproceedings{3d-retr,
  author    = {Zai Shi, Zhao Meng, Yiran Xing, Yunpu Ma, Roger Wattenhofer},
  title     = {3D-RETR: End-to-End Single and Multi-View3D Reconstruction with Transformers},
  booktitle = {BMVC},
  year      = {2021}
}

Create Environment

git clone [email protected]:FomalhautB/3D-RETR.git
cd 3D-RETR
conda env create -f config/environment.yaml
conda activate 3d-retr

Prepare Data

ShapeNet

Download the Rendered Images and Voxelization (32) and decompress them into $SHAPENET_IMAGE and $SHAPENET_VOXEL

Train

Here is an example of reproducing the result of the single view 3D-RETR-B on the ShapeNet dataset:

python train.py \
    --model image2voxel \
    --transformer_config config/3d-retr-b.yaml \
    --annot_path data/ShapeNet.json \
    --model_path $SHAPENET_VOX \
    --image_path $SHAPENET_IMAGES \
    --gpus 1 \
    --precision 16 \
    --deterministic \
    --train_batch_size 16 \
    --val_batch_size 16 \
    --num_workers 4 \
    --check_val_every_n_epoch 1 \
    --accumulate_grad_batches 1 \
    --view_num 1 \
    --sample_batch_num 0 \
    --loss_type dice \

3D-RETR: End-to-End Single and Multi-View3D Reconstruction with Transformers

Related tags

Overview

3D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformers (BMVC 2021)

Zai Shi, Zhao Meng, Yiran Xing, Yunpu Ma, Roger Wattenhofer

Citation

Create Environment

Prepare Data

ShapeNet

Train

Owner

Zai Shi

PyTorch wrappers for using your model in audacity!

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

Reformer, the efficient Transformer, in Pytorch

Code snippets created for the PyTorch discussion board

A few Windows specific scripts for PyTorch

Fast and Easy-to-use Distributed Graph Learning for PyTorch Geometric

Kaldi-compatible feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Use Jax functions in Pytorch with DLPack

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

This is an differentiable pytorch implementation of SIFT patch descriptor.

ocaml-torch provides some ocaml bindings for the PyTorch tensor library.

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

On the Variance of the Adaptive Learning Rate and Beyond

Official implementations of EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis.

lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch

A PyTorch implementation of EfficientNet

A tutorial on "Bayesian Compression for Deep Learning" published at NIPS (2017).

3D-RETR: End-to-End Single and Multi-View3D Reconstruction with Transformers

Related tags

Overview

3D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformers (BMVC 2021)

Zai Shi*, Zhao Meng*, Yiran Xing, Yunpu Ma, Roger Wattenhofer

Citation

Create Environment

Prepare Data

ShapeNet

Train

Owner

Zai Shi

PyTorch wrappers for using your model in audacity!

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

Reformer, the efficient Transformer, in Pytorch

Code snippets created for the PyTorch discussion board

A few Windows specific scripts for PyTorch

Fast and Easy-to-use Distributed Graph Learning for PyTorch Geometric

Kaldi-compatible feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Use Jax functions in Pytorch with DLPack

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

This is an differentiable pytorch implementation of SIFT patch descriptor.

ocaml-torch provides some ocaml bindings for the PyTorch tensor library.

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

On the Variance of the Adaptive Learning Rate and Beyond

Official implementations of EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis.

lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch

A PyTorch implementation of EfficientNet

A tutorial on "Bayesian Compression for Deep Learning" published at NIPS (2017).

Zai Shi, Zhao Meng, Yiran Xing, Yunpu Ma, Roger Wattenhofer