VCL3D/PanoDR
Code and models for "PanoDR: Spherical Panorama Diminished Reality for Indoor Scenes" presented at the OmniCV workshop of CVPR21.
This project helps interior designers, architects, or virtual tour creators remove unwanted objects from 360-degree panoramic images of indoor spaces. You provide a panoramic image and a mask indicating the object to remove, and it generates a new panorama where the object is seamlessly erased, creating a clean, unobstructed view. This is ideal for refining virtual property tours or visualizing spaces without clutter.
No commits in the last 6 months.
Use this if you need to digitally 'clean up' spherical indoor panoramas by removing specific items without leaving noticeable gaps or distortions.
Not ideal if you need to remove objects from standard flat photos or outdoor panoramic scenes.
Stars
39
Forks
7
Language
Python
License
—
Category
Last pushed
Mar 21, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/VCL3D/PanoDR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.