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

Use Jax functions in Pytorch with DLPack

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

An optimizer that trains as fast as Adam and as good as SGD.

Code for paper "Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking"

PyTorch implementations of normalizing flow and its variants.

S3-plugin is a high performance PyTorch dataset library to efficiently access datasets stored in S3 buckets.

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

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

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

Implements pytorch code for the Accelerated SGD algorithm.

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

Model summary in PyTorch similar to `model.summary()` in Keras

TorchShard is a lightweight engine for slicing a PyTorch tensor into parallel shards

A few Windows specific scripts for PyTorch

A lightweight wrapper for PyTorch that provides a simple declarative API for context switching between devices, distributed modes, mixed-precision, and PyTorch extensions.

You like pytorch? You like micrograd? You love tinygrad! ❤️

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

PyTorch extensions for fast R&D prototyping and Kaggle farming

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

Use Jax functions in Pytorch with DLPack

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

An optimizer that trains as fast as Adam and as good as SGD.

Code for paper "Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking"

PyTorch implementations of normalizing flow and its variants.

S3-plugin is a high performance PyTorch dataset library to efficiently access datasets stored in S3 buckets.

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

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

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

Implements pytorch code for the Accelerated SGD algorithm.

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

Model summary in PyTorch similar to `model.summary()` in Keras

TorchShard is a lightweight engine for slicing a PyTorch tensor into parallel shards

A few Windows specific scripts for PyTorch

A lightweight wrapper for PyTorch that provides a simple declarative API for context switching between devices, distributed modes, mixed-precision, and PyTorch extensions.

You like pytorch? You like micrograd? You love tinygrad! ❤️

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

PyTorch extensions for fast R&D prototyping and Kaggle farming

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