Robbyant / Robbyant/lingbot-map
Error processing example: 'world_points_from_depth'
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.1k
- Forks
- 1.9k
- PR merge metrics
- No merged PRs in 30d
Description
I did try to save a glb out of the model I did run :
python demo_render/batch_demo.py --model_path models/lingbot-map.pt --input_folder example/courthouse --mask_sky --use_sdpa --save_predictions --output_folder out --save_glb
And I got ;
Building GLB scene
Using Pointmap Branch
Warning: world_points not found, falling back to depth-based points
Error processing courthouse : 'world_points_from_depth'
I did not save the video nor the glb.
when I log the predictions given to the export_glb() function I got :
{
"pose_enc" : np.array
"depth" : np.array
"depth_conf" : np.array
"extrinsic" : np.array
"intrinsic" : np.array
"images" np.array
}
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with demo_render/batch_demo.py and the export_glb() entry point, then reproduce the reported command using example/courthouse. Inspect how the predictions dictionary is passed through the depth-based fallback and where the 'world_points_from_depth' error is raised. Done means the example processes successfully and saves the requested video and GLB.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100