Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility ICCV2021

Last update: Dec 25, 2022

Related tags

Deep Learning vis2mesh

Overview

Vis2Mesh

This is the offical repository of the paper:

Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility

https://arxiv.org/abs/2108.08378

@misc{song2021vis2mesh,
      title={Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility}, 
      author={Shuang Song and Zhaopeng Cui and Rongjun Qin},
      year={2021},
      eprint={2108.08378},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Updates

2021/9/6: Intialize all in one project. Only this version only supports inferencing with our pre-trained weights. We will release Dockerfile to relief deploy efforts.

TODO

Ground truth generation and network training.
Evaluation scripts

Build With Docker (Recommended)

Install nvidia-docker2

# Add the package repositories
distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list

sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit
sudo systemctl restart docker

Build docker image

docker build . -t vis2mesh

Build on Ubuntu

Please create a conda environment with pytorch and check out our setup script:

./setup_tools.sh

Usage

Get pretrained weights and examples

pip install gdown
./checkpoints/get_pretrained.sh
./example/get_example.sh

Run example

The main command for surface reconstruction, the result will be copied as $(CLOUDFILE)_vis2mesh.ply.

python inference.py example/example1.ply --cam cam0

We suggested to use docker, either in interactive mode or single shot mode.

xhost +
name=vis2mesh
# Run in interactive mode
docker run -it \
--mount type=bind,source="$PWD/checkpoints",target=/workspace/checkpoints \
--mount type=bind,source="$PWD/example",target=/workspace/example \
--privileged \
--net=host \
-e NVIDIA_DRIVER_CAPABILITIES=all \
-e DISPLAY=unix$DISPLAY \
-v $XAUTH:/root/.Xauthority \
-v /tmp/.X11-unix:/tmp/.X11-unix:rw \
--device=/dev/dri \
--gpus all $name

cd /workspace
python inference.py example/example1.ply --cam cam0

# Run with single shot call
docker run \
--mount type=bind,source="$PWD/checkpoints",target=/workspace/checkpoints \
--mount type=bind,source="$PWD/example",target=/workspace/example \
--privileged \
--net=host \
-e NVIDIA_DRIVER_CAPABILITIES=all \
-e DISPLAY=unix$DISPLAY \
-v $XAUTH:/root/.Xauthority \
-v /tmp/.X11-unix:/tmp/.X11-unix:rw \
--device=/dev/dri \
--gpus all $name \
/workspace/inference.py example/example1.ply --cam cam0

Run with Customize Views

python inference.py example/example1.ply Run the command without --cam flag, you can add virtual views interactively with the following GUI. Your views will be recorded in example/example1.ply_WORK/cam*.json.

Navigate in 3D viewer and click key [Space] to record current view. Click key [Q] to close the window and continue meshing process.

Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility ICCV2021

Related tags

Overview

Vis2Mesh

Updates

TODO

Build With Docker (Recommended)

Install nvidia-docker2

Build docker image

Build on Ubuntu

Usage

Get pretrained weights and examples

Run example

Run with Customize Views

Owner

City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones Code

RealTime Emotion Recognizer for Machine Learning Study Jam's demo

Python Classes: Medical Insurance Project using Object Oriented Programming Concepts

Implementation of the paper "Language-agnostic representation learning of source code from structure and context".

[NeurIPS-2021] Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation

[RSS 2021] An End-to-End Differentiable Framework for Contact-Aware Robot Design

My course projects for the 2021 Spring Machine Learning course at the National Taiwan University (NTU)

Deep Networks with Recurrent Layer Aggregation

Using Clinical Drug Representations for Improving Mortality and Length of Stay Predictions

Retrieve and analysis data from SDSS (Sloan Digital Sky Survey)

Monify: an Expense tracker Program implemented in a Graphical User Interface that allows users to keep track of their expenses

TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios

PyTorch implementation for NED. It can be used to manipulate the facial emotions of actors in videos based on emotion labels or reference styles.

General Virtual Sketching Framework for Vector Line Art (SIGGRAPH 2021)

The implementation code for "DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction"

Does MAML Only Work via Feature Re-use? A Data Set Centric Perspective

Experiments on continual learning from a stream of pretrained models.

Implementation of Cross Transformer for spatially-aware few-shot transfer, in Pytorch

HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks

Final Project for the CS238: Decision Making Under Uncertainty course at Stanford University in Autumn '21.