ike-taku Goto Github PK

bingham-rotation-learning

A Smooth Representation of SO(3) for Deep Rotation Learning with Uncertainty.

blender_server

blenderproc

A procedural blender pipeline to generate images for deep learning

bpnp

Back-propagatable PnP

catalyst

Accelerated DL R&D

chamfer_distance

Implementation of the Chamfer Distance as a module for PyTorch

chamferdist

Pytorch package to compute Chamfer distance between point sets (pointclouds).

clean-pvnet

Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral

contrastive-unpaired-translation

Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

cupoch

CUDA-based 3D data processing and robotics library

deep_bingham

Code for "Deep Orientaton Uncertainty Learning based on a Bingham Loss" (ICLR2020)

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

dib-r

Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer (NeurIPS 2019)

dino-vit-features

Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".

drake

Model-based design and verification for robotics.

drit_hr

Multi-Modal Image-to-Image Translation on Tasks with High-Resolution Images

egpu-switcher

🖥🐧 Setup script for eGPUs in Linux (X.Org)

epro-pnp

[CVPR 2022 Oral, Best Student Paper] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

gaussian-slam

Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting

gaussian-splatting-lightning

gcgan

grasp_diffusion

Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home

gsplat

CUDA accelerated rasterization of gaussian splatting

librealsense

Intel® RealSense™ SDK

mdmm

Learning multi-domain multi-modality I2I translation

mean_average_precision

Mean Average Precision for Object Detection

mesh_utils

nafnet

The state-of-the-art image restoration model without nonlinear activation functions.

nerfstudio

A collaboration friendly studio for NeRFs

objectdatasettools

Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera. This project prepares training and testing data for various deep learning projects such as 6D object pose estimation projects singleshotpose, as well as object detection and instance segmentation projects.