gap-lab-cuhk-sz / sampro3d Goto Github PK
View Code? Open in Web Editor NEWSAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Scene Segmentation
Home Page: https://mutianxu.github.io/sampro3d/
License: Apache License 2.0
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Scene Segmentation
Home Page: https://mutianxu.github.io/sampro3d/
License: Apache License 2.0
Thanks for your excellent work. Can you please tell me what is the filtering strategy in automatic-SAM mentioned in the paper? I didn't find the filtering strategy in segment anything.
Thank you for your excellent work. I've noticed that you've employed a new method to obtain quantitative results, but I haven't seen this part in the code. Could you please share this portion of the code?
Thanks.
Hi,
Thanks for your great work. I tried to test it on the RedWood bedroom dataset (http://redwood-data.org/indoor_lidar_rgbd/index.html) with downsampled RGB-D images (from 21930 to 219 frames, resolution 640x480), both original and downsampled pointcloud (~5M, 100k points) but cannot get reasonable outputs. After filtering it seems that only the first frame result is remained as I checked the camera pose by reprojecting the first frame depth into the scene scan point cloud. It says originally with 580 prompts in 3d proposal stage and 51 remains after 2d-guided filter. Then 15 after prompt consolidation.
There is one point I don't know whether I got it correct: in utils/main_utils.py:transform_pt_depth_scannet_torch(), it requires bx and by from camera intrinsic matrix. I don't know what they mean and set them to 0s.
Could you provide any insights on refining the results? e.g. lower image resolution for SAM, change filter parameters, etc.
Final segmented point cloud, the floor is segmented well, but for other parts seem only around the first frame viewpoint:
Hello!
Thank you for your wonderful work. I have encountered the following two bugs in my reproduction, in which I have not changed any core code.
The first bug I encountered was when I followed the steps to run "main.py":
Line 165 in 2733583
mask_2d_3d = mask[mapping[:, 0].type(torch.long), mapping[:, 1].type(torch.long)]
I encountered the second bug after resolving the first one:
So I fixed the bug by moving line 377 before line 358.
Line 377 in 2733583
Hope these get your attention. @mutianxu
Thank you and your team for the wonderful work! I've successfully run the code, but how can I visualize the 3D bounding boxes?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.