BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation

Yuanhong Yu1,3Xingyi He1,3Chen Zhao4Junhao Yu5Jiaqi Yang6Ruizhen Hu7Yujun Shen3Xing Zhu3Xiaowei Zhou1Sida Peng1,2

1State Key Lab of CAD & CG, Zhejiang University    2Xiangjiang Laboratory    3Ant Group    4EPFL    5Chongqing University    6Northwestern Polytechnical University    7Shenzhen University   

Paper    Project Page    Code

This interactive demo allows you to estimate 6DoF object poses with in-the-wild images.

Try an Example Video
🎨 Annotation Tools
1 15
Reconstructor
  • Point Mode: Click to add foreground points
  • Bounding Box Mode: First click sets top-left, second click sets bottom-right
  • Only one object is supported for annotation and prediction
  • Camera intrinsics are estimated from reference images using DUSt3R