vincentfung13/MINE
Code and models for our ICCV 2021 paper "MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis"
This tool helps researchers and visual effects artists create immersive virtual scenes from just a single photograph. By taking one image as input, it reconstructs a detailed 3D representation of the scene, allowing for the generation of new views as if the camera were moving. This is ideal for those working with 3D scene reconstruction or novel view synthesis.
423 stars. No commits in the last 6 months.
Use this if you need to generate multiple viewpoints or a video fly-through of a scene using only one input image.
Not ideal if you require real-time processing or are working with complex, dynamic scenes that change over time.
Stars
423
Forks
43
Language
Python
License
MIT
Category
Last pushed
Sep 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/vincentfung13/MINE"
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.