SurfelWarp

SurfelWarp is a dynamic reconstruction pipeline. Compared to other dynamic reconstruction methods like DynamicFusion, surfelwarp uses flat surfel array (instead of volumetric field) as the geometry representation, which makes the pipeline robust and efficient. The approach is described in our paper.

Demo [Video][Presentation]

Publication

Wei Gao and Russ Tedrake, "SurfelWarp: Efficient Non-Volumetic Single View Dynamic Reconstruction", Robotics: Science and Systems (RSS) 2018 [Project][Paper][Presentation]

Build Instructions

The code was originally developed with

CUDA 9

PCL 1.8

CUDA

According to your environment, please follow the specific build instruction:

• Ubuntu 16.04 with

  CUDA 9

  (note that

  CUDA 10

  doesn't work with this one)
• Ubuntu 16.04/18.04 with

  CUDA >= 9

  (

  CUDA 10

  is OK) and

  cilantro

• Windows 10 with

  CUDA 9

  (

  CUDA 10

  doesn't work with this one)
• Windows 10 with

  CUDA >= 9

  (

  CUDA 10

  is OK) and

  cilantro

We also provide a pre-built binary for the windows platform (The CUDA

-arch

sm_60

Run Instructions

We use the VolumeDeform dataset to illustrate how to run the code. An example configuration file is provided here for the "boxing" sequence. First, you need to download the boxing sequence from the VolumeDeform dataset and extract it to

data_root

${data_root}/frame-000000.color.png
${data_root}/frame-000000.depth.png
...

You also need to download the trained model for Global Patch Collider (gpc) from here. Let the path to the model be

${gpc_path}

In the configuration file, please modify the

data_prefix

gpc_model_path

${data_root}

${gpc_path}

cd ${project_root}/build/apps/surfelwarp_app
./surfelwarp_app /path/to/config

If everything goes well, the executable would produce the reconstructed result per frame in the same folder as

surfelwarp_app

FAQ

• What's the typical speed of surfelwarp?

On the windows platform with a Nvidia Titan Xp GPU, the processing time is usually less than 20 [ms] per frame. To test the speed in surfelwarp_app, you need to build with Release and disable offline rendering (which takes most of the time).

• How to use my own data?

You might override the FetchInterface and use it with ImageProcessor. If you don't have performance requirement, you can also convert your data into the format of VolumeDeform.

• How to deal with topology change?

Currently, only periodic reinitialization is implemented. To use it, set this flag in config file. More advanced criterion of reinitialization would come soon.

TODO

The code is re-factored and improved from the repo of our RSS paper. There are some planned new features and some old code need to be ported into this repository. Here is a list of TODOs:

• [x] Add sparse feature correspondence
• [x] Implement albedo reconstruction
• [ ] Rewrite automatic reinitialization detection for the new geometry and loss function. Currently, only periodic reinitialization is implemented
• [ ] Port the GPU kdtree querying (although the overall speed is already relatively fast)

Contact

If you have any question or suggestion regarding this work, please send me an email.