astra-vision/SceneRF
[ICCV 2023] Official implementation of "SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields"
This project helps perception engineers or robotics developers reconstruct detailed 3D scenes from a single video camera feed. You input monocular video sequences of environments like streets or indoor spaces, and it outputs a rich 3D representation, including depth maps and novel views. This is useful for anyone building autonomous systems that need to understand and interact with their physical surroundings.
379 stars. No commits in the last 6 months.
Use this if you need to generate dense 3D models and synthesize new views of a scene using only standard video camera input, without requiring specialized depth sensors.
Not ideal if you require real-time 3D reconstruction on low-power edge devices or if high-precision metric accuracy across extremely large, unbounded environments is your primary concern.
Stars
379
Forks
33
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/astra-vision/SceneRF"
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.