IGLICT/IBSR_jittor
Code for 'Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning', ICCV 2021
This project helps computer vision researchers and 3D content creators find the most similar 3D object from a collection based on a single 2D image. You input a 2D image, and it outputs a highly matched 3D shape, even for complex objects. It’s for anyone working with object recognition, 3D modeling, or virtual environments who needs to quickly bridge the gap between 2D visuals and 3D assets.
No commits in the last 6 months.
Use this if you need to identify or retrieve a 3D model corresponding to a particular object shown in a 2D photograph.
Not ideal if you need to reconstruct a 3D shape from scratch or require precise 3D measurements from a 2D image.
Stars
62
Forks
11
Language
Python
License
MIT
Category
Last pushed
Apr 01, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/IGLICT/IBSR_jittor"
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.