shubhtuls/mvcSnP
Code release for "Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction"
This project helps computer vision researchers automatically reconstruct the 3D shape and orientation of objects from multiple 2D images. You input several standard 2D images of an object, and it outputs a 3D model of that object along with its precise pose (position and orientation) in 3D space. It's designed for researchers working on 3D computer vision tasks.
118 stars. No commits in the last 6 months.
Use this if you need to infer the 3D shape and pose of objects from diverse 2D image perspectives without explicit 3D supervision.
Not ideal if you're looking for an out-of-the-box solution for non-research applications or if you lack experience with deep learning frameworks like Torch.
Stars
118
Forks
11
Language
Lua
License
—
Category
Last pushed
Jan 04, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/shubhtuls/mvcSnP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vita-epfl/monoloco
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social...
fangchangma/self-supervised-depth-completion
ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and...
nburrus/stereodemo
Small Python utility to compare and visualize the output of various stereo depth estimation algorithms
JiawangBian/sc_depth_pl
SC-Depth (V1, V2, and V3) for Unsupervised Monocular Depth Estimation ...
wvangansbeke/Sparse-Depth-Completion
Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st...