The branch contains STream3R[α], a metric-scale model built on top of DUSt3R.
The codebase may be somewhat unpolished.

Checkpoint

The checkpoint can be downloaded from here.

📈 Evaluation

The evaluation follows MonST3R and Spann3R, CUT3R.

1. Prepare Evaluation Dataset

   We follow the dataset preparation guides from MonST3R and Spann3R to prepare the datasets. For convenience, we provide the processed datasets on Hugging Face, which can be downloaded directly.

   The datasets should be organized as follows under the root directiory of the project:

   data/
   ├── 7scenes
   ├── bonn
   ├── kitti
   ├── neural_rgbd
   ├── nyu-v2
   ├── scannetv2
   ├── sintel
   └── tum
   

2. Run Evaluation

   Use the provided scripts to evaluate different tasks.

   Please change the model weight path accordingly.

   Monodepth

   bash eval/monodepth/run.sh

   Video Depth

   bash eval/video_depth/run.sh

   Camera Pose Estimation

   bash eval/relpose/run.sh

   Multi-view Reconstruction

   bash eval/mv_recon/run.sh