Robust Speech Recognition via Large-Scale Weak Supervision

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

基于Python的开源量化交易平台开发框架

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Azur Lane bot (CN/EN/JP/TW) 碧蓝航线脚本 | 无缝委托科研，全自动大世界

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

StyleGAN2-ADA - Official PyTorch implementation

Differentiable architecture search for convolutional and recurrent networks

😺 A tool designed to shorten steps needed to import and optimize models into VRChat. Compatible models are: MMD, XNALara, Mixamo, DAZ/Poser, Blender Rigify, Sims 2, Motion Builder, 3DS Max and pote…

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

Visual localization made easy with hloc

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

Automated Deep Learning: Neural Architecture Search Is Not the End (a curated list of AutoDL resources and an in-depth analysis)

PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)

Grounding Image Matching in 3D with MASt3R

Code release for NeuS

Automated deep learning algorithms implemented in PyTorch.

Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)

Tooling for the Common Objects In 3D dataset.

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Network Slimming (Pytorch) (ICCV 2017)

Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes (CVPR 2021 Oral)

Multi-view 3D reconstruction using neural rendering. Unofficial implementation of UNISURF, VolSDF, NeuS and more.

From Coarse to Fine: Robust Hierarchical Localization at Large Scale with HF-Net (https://arxiv.org/abs/1812.03506)

Implementations of NeRF variants based on Taichi + PyTorch

A Change Detection Repo Standing on the Shoulders of Giants

[768 Resolution] [Any "SDXL" Model] [Various Conditions] [Arbitrary Views] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"

PyTorch implementation of NetVLAD & Online Hardest Triplet Loss.