8000 GitHub - xiahongchi/DRAWER
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

xiahongchi/DRAWER

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DRAWER logo DRAWER: Digital Reconstruction and Articulation With Environment Realism


1University of Illinois Urbana-Champaign, 2University of Washington, 3Allen Institute for AI, 4Cornell University

CVPR 2025

Environment

Our code repo needs to setup three environments.

  1. For SDF Reconstruction, please follow the instructions Here.

  2. For Gaussian Splat Reconstruction, please follow the instructions Here.

  3. For Isaac Sim, please follow the instructions Here.

Data

  • We provide the data we collected in UIUC and UW, which can be downloaded from Here.

  • We provide our door tracking evaluation data Here.

Checkpoints

We provide the download links of checkpoints of foundation models we used Here.

Usage

DRAWER is a system with multiple stages. We provide a guidance for the usage of our code stage-by-stage (SDF Reconstruction, 3D Based Perception, Isaac Sim Simulation, and Gaussian Splat Reconstruction) and the whole system altogether Here.

We also provide the scripts for the usage of our dual representation reconstruction. Please directly check Here.

For the whole system usage, here is a brief explanation:

Stage 1: SDF Reconstruction:

  • Use diffusion-e2e-ft to generate monocular normal and depth priors.

  • Use an improved version of BakedSDF based on SDFStudio to run sdf reconstruction.

Stage 2: 3D Based Perception:

  • Use Grounded SAM to recognize drawers and cabinet doors in the scene.

  • Use graph based method and GPT-4o to filter and finalize the 2d locations of doors. (We suggest double checking with the perception results, since it's not perfect and could lead to failure cases, and please refer to note Here.)

  • Use 3DOI to infer the articulation information.

  • Fit drawer and cabinet doors to correct 3d location.

Stage 3: Isaac Sim Simulation:

  • Transform the scene into USD file format.

  • Simulate the scene dynamics and attain the trajectory of doors.

Stage 4: Gaussian Splat Reconstruction:

  • Run our Gaussian on Mesh reconstruction developed based on NeRFStudio.

  • Use Matfuse to generate textures.

  • Merge Gaussian Splats of the scene and the cabinets.

Applications

DRAWER has applications including:

  • Use scripts Here to export Gaussians of the scene and each doors, which could be loaded into Unreal Engine with Lama AI Plugin.

  • Real-to-Sim-to-Real Training: Please use the scripts Here to generate usd file for isaac lab and refer to the code Here.

Progress

  • SDF Reconstruction
  • Perception
  • Isaac Sim Simulation
  • Gaussian Splat on Mesh
  • Data Release
  • Real-to-Sim-to-Real Training

Contact

Contact Hongchi Xia if you have any further questions.

Acknowledgments

Our codebase builds heavily on SDFStudio, NeRFStudio, diffusion-e2e-ft, Grounded SAM, 3DOI, and Matfuse. Thanks for open-sourcing!

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0