hwjiang1510/LEAP
[ICLR 2024] Code for LEAP: Liberate Sparse-view 3D Modeling from Camera Poses
This tool helps 3D artists, game developers, or anyone needing 3D models create them from just a few pictures, without needing to know exactly where those pictures were taken. You provide a few images of an object, and it generates a detailed 3D model of that object. It's ideal for quickly digitizing real-world objects into 3D assets.
190 stars. No commits in the last 6 months.
Use this if you need to generate high-quality 3D models from a limited set of images and want to skip the complex step of precisely calculating camera positions for each photo.
Not ideal if you need perfectly accurate density predictions on real-world images, as the model trained on Omniobject3D may struggle; consider using Kubric pre-trained weights for such scenarios.
Stars
190
Forks
6
Language
Python
License
—
Category
Last pushed
May 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/hwjiang1510/LEAP"
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.