AutoSweep: Recovering 3D Editable Objects from a Single Photo
Fully automatic framework for extracting editable 3D objects directly from a single photograph.
3d autosweep object-generation computer-vision research article paper arxiv:2005.13312

Don't forget to tag @ShanghaiTechVRVC in your comment, otherwise they may not be notified.

Authors community post
The Virtual Reality and Visual Computing Center of ShanghaiTech University
Share this project
Similar projects
PIFuHD: High-Resolution 3D Human Digitization
This repository contains a pytorch implementation of "Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization".
Medical Zoo - 3D Multi-modal Medical Image Segmentation
My articles on deep learning in medical imaging
Epipolar Transformers
Differentiable "epipolar transformer", which enables the 2D detector to leverage 3D-aware features to improve 2D pose estimation.
Beyond the Pixel Plane: Sensing and Learning in 3d
Recent deep learning techniques that enable 3D object classification and semantic segmentation.
Top collections