LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model (CVPR2024)

[MICCAI ISIC Workshop 2024 (Honorable Mention)] From Majority to Minority: A Diffusion-based Augmentation for Underrepresented Groups in Skin Lesion Analysis

A General-Purpose Multimodal Foundation Model for Dermatology

Vision-based GNSS-Free Localization for UAVs in the Wild

Code for "Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation"

A suite of image and video neural tokenizers

Code for the CVPR 2024 paper highlight and demo "PIGEON: Predicting Image Geolocations".

[3DV'25] 3D Reconstruction with Spatial Memory

Statewide Visual Geolocalization in the Wild (ECCV 2024)

This is an official PyTorch implementation of our NeurIPS 2023 paper "GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization"

MDM-bypass

iOS /iPadOS 16.0 - 18.0 / 18.1 beta 4, An ultimate customization tool, uilitizing the bug that makes TrollRestore possible.

Download, model, analyze, and visualize street networks and other geospatial features from OpenStreetMap.

This WebApp allows users to control Eight Sleep mattresses without a subscription by using a custom scheduling system. It runs a script every 30 minutes to adjust mattress temperature according to …

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

SEED-Voken: A Series of Powerful Visual Tokenizers

Implementation of MagViT2 Tokenizer in Pytorch

The repo of Street View Image, Pose, and 3D Cities Dataset. Used in "Generic 3D Representation via Pose Estimation and Matching", ECCV16

DUSt3R: Geometric 3D Vision Made Easy

Grounding Image Matching in 3D with MASt3R

simple code to download images in a mapillary sequence

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