-
Univ. Tokyo / Preferred Networks
- Tokyo, Japan
- http://hiroharu-kato.com/
Stars
An academic project page template powered by React + UIKit, w/ markdown and KaTeX support
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
Specification and reference implementation for the OpenPBR Surface shading model
Python library for video editing, presentation video generation, motion graphics, shader art coding, and other video production tasks
A playbook for systematically maximizing the performance of deep learning models.
Browser extension which gives you more control over your Twitter timeline and adds missing features and UI improvements - for desktop and mobile
Blender Python scripts for rendering images directly from command-line interface
Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering
Code repository for the paper: "Coherent Reconstruction of Multiple Humans from a Single Image" in CVPR'20
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
Chainer/PyTorch Migration Library
Various CNN models for CIFAR10 with Chainer
Differentiable rendering without approximation.
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images. In ECCV2018.
A PyTorch port of the Neural 3D Mesh Renderer
Project repo for Learning Category-Specific Mesh Reconstruction from Image Collections
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation [Inoue+, CVPR2018].
Code release for "Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency" (CVPR 2017)
This repository contains the source codes for the paper "AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud + connectivity)…
Open3D: A Modern Library for 3D Data Processing
Code for Learnt Stereo Machines based on the NIPS 2017 paper
A resource repository for 3D machine learning





