zubair-irshad/shapo
Pytorch code for ECCV'22 paper. ShAPO: Implicit Representations for Multi-Object Shape, Appearance and Pose Optimization
This project helps robotics engineers and researchers precisely reconstruct the 3D shape, appearance, and pose of multiple objects from a single camera view. You provide an RGB-D image (color and depth) of a scene, and it outputs detailed 3D models with their textures and exact positions in space. It's designed for professionals working with robotic vision, augmented reality, or 3D scene understanding.
196 stars. No commits in the last 6 months.
Use this if you need highly accurate 3D reconstructions and pose estimations of multiple objects in a complex scene from a single image.
Not ideal if you only need rough object detection or 2D image segmentation, or if you don't have access to depth camera data.
Stars
196
Forks
13
Language
Python
License
—
Category
Last pushed
Jun 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/zubair-irshad/shapo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
patrikhuber/eos
A lightweight 3D Morphable Face Model library in modern C++
Uason-Chen/CTR-GCN
[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for...
PeterL1n/BackgroundMattingV2
Real-Time High-Resolution Background Matting
PeterL1n/RobustVideoMatting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Zielon/MICA
MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]