Amir-Arsalan/Synthesize3DviaDepthOrSil
[CVPR 2017] Generation and reconstruction of 3D shapes via modeling multi-view depth maps or silhouettes
This project helps researchers and engineers generate and reconstruct 3D shapes from 2D images. By feeding in multi-view depth maps or silhouettes of an object, it can either create new 3D models or reconstruct an existing one. This is useful for anyone working with 3D model generation, computer vision, or graphics, such as academics in computational imaging or professionals in 3D design.
169 stars. No commits in the last 6 months.
Use this if you need to create novel 3D shapes or reconstruct existing ones from various 2D perspectives, using either depth information or object outlines.
Not ideal if you do not have multi-view depth maps or silhouette images as input, or if you need a high-performance, ready-to-deploy solution for real-time applications.
Stars
169
Forks
32
Language
Lua
License
MIT
Category
Last pushed
Jun 17, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Amir-Arsalan/Synthesize3DviaDepthOrSil"
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.