Skip to content

Latest commit

 

History

History
36 lines (32 loc) · 1.99 KB

README.md

File metadata and controls

36 lines (32 loc) · 1.99 KB

Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction

Xiaoyang Lyu* · Chirui Chang* · Peng Dai · Yang-Tian Sun · Xiaojuan Qi

*Equal Contributions

CVPR 2024

Logo

TL; DR: Scene reconstruction from multi-view images is a fundamental problem in computer vision and graphics. Recent neural implicit surface reconstruction methods have achieved high-quality results; however, editing and manipulating the 3D geometry of reconstructed scenes remains challenging due to the absence of naturally decomposed object entities and complex object/background compositions. In this paper, we present Total-Decom, a novel method for decomposed 3D reconstruction with minimal human interaction. Our approach seamlessly integrates the Segment Anything Model (SAM) with hybrid implicit-explicit neural surface representations and a mesh-based region-growing technique for accurate 3D object decomposition. Total-Decom requires minimal human annotations while providing users with real-time control over the granularity and quality of decomposition. We extensively evaluate our method on benchmark datasets and demonstrate its potential for downstream applications, such as animation and scene editing.


TODO

  • Create the project page
  • Opensource all the training code
  • Opensource the GUI
  • Downstream applications