A latent text-to-image diffusion model

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

A collection of various deep learning architectures, models, and tips

Companion webpage to the book "Mathematics For Machine Learning"

High-Resolution Image Synthesis with Latent Diffusion Models

Convert AI papers to GUI，Make it easy and convenient for everyone to use artificial intelligence technology。让每个人都简单方便的使用前沿人工智能技术

This repository contains demos I made with the Transformers library by HuggingFace.

PyTorch code and models for the DINOv2 self-supervised learning method.

Multi-Joint dynamics with Contact. A general purpose physics simulator.

Solve puzzles. Learn CUDA.

Acceptance rates for the major AI conferences

[ICCV 2019] Monocular depth estimation from a single image

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

functorch is JAX-like composable function transforms for PyTorch.

Tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation (http://fcn.berkeleyvision.org)

Takagi and Nishimoto, CVPR 2023

GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting (SIGGRAPH Asia 2024, TOG)

Language-Driven Semantic Segmentation

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers. (ICCV 2021 Oral)

We extend Segment Anything to 3D perception by combining it with VoxelNeXt.