dazinovic/neural-rgbd-surface-reconstruction
Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"
This project helps create detailed 3D models of real-world environments from video data. It takes in a sequence of color images (RGB) and corresponding depth images, along with camera positioning information, to produce a precise 3D surface reconstruction of the scene. This tool is ideal for computer vision researchers or 3D graphics professionals working with spatial data.
625 stars. No commits in the last 6 months.
Use this if you need to generate high-fidelity 3D surface models from RGB-D video streams for analysis or visualization.
Not ideal if you only have standard 2D images without depth information or precise camera poses.
Stars
625
Forks
58
Language
Python
License
—
Category
Last pushed
Aug 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/dazinovic/neural-rgbd-surface-reconstruction"
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.