-
Intel Labs
- Santa Clara, CA
Starred repositories
3D U-Net model for volumetric semantic segmentation written in pytorch
A cross-platform, high performance renderer for Gaussian Splatting using Vulkan Compute. Supports ✅ Windows, Linux, macOS, iOS, and visionOS
SYCL implementation of Fused MLPs for Intel GPUs
Library for reading & writing the E57 file format
Intel® Extension for DeepSpeed* is an extension to DeepSpeed that brings feature support with SYCL kernels on Intel GPU(XPU) device. Note XPU is already supported in stock DeepSpeed (upstream).
Intel® AI Reference Models: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors and Intel® Data Center GPUs
Find and copy needed dynamic libraries into python wheels
Android application for capture of Video, IMU data and Camera data useful in SLAM and Structure from Motion research. Differs between Optical Image Stabilization (OIS) and Digital Video Stabilizati…
Open3D: A Modern Library for 3D Data Processing
SPEAR: A Simulator for Photorealistic Embodied AI Research
QuadTree Attention for Vision Transformers (ICLR2022)
oneAPI Threading Building Blocks (oneTBB)
Tiny, dependency-free USDZ/USDA/USDC library written in C++14
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
[T-PAMI 2022] Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
PyTorch extensions for high performance and large scale training.
A simulation library for Agility Robotics' Cassie robot using MuJoCo
Quick Look extension for highlight source code files on macOS 10.15 and later.
3D Bounding Box Annotation Tool (3D-BAT) Point cloud and Image Labeling
A curated list of awesome data labeling tools
oneAPI Deep Neural Network Library (oneDNN)
OpenMMLab Detection Toolbox and Benchmark
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.