A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

[ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

Unofficial implementation of the paper "The Chosen One: Consistent Characters in Text-to-Image Diffusion Models"

[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning

[CVPR'24] NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild

Welcome to the project repository for POPE (Promptable Pose Estimation), a state-of-the-art technique for 6-DoF pose estimation of any object in any scene using a single reference.

A cli program of image retrieval using dinov2

A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models.

[NeurIPS'24] A Simple Image Segmentation Framework via In-Context Examples

AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2

Official implementation of the paper 'Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery'

DINOv2 module for use with Autodistill.

The inference of DINOv2 ONNX models using the ONNXRuntime library.

Explore the cutting edge of computer vision with this comprehensive repository, showcasing a spectrum from classical machine learning to state-of-the-art transformer models.

The official source code of paper in ECCV 2024. "Aligning Neuronal Coding of Dynamic Visual Scenes with Foundation Vision Models"

Re-identify animals from cam trap images

An open-source implementaion for fine-tuning DINOv2 by Meta.

Implementation of Fréchet Distance with DINOv2 backbone in Pytorch.

This repository contains the code implementation used in the paper: "Human-in-the-Loop Segmentation of Multi-species Coral Imagery".

Clustering images of skin diseases using DINOv2 embeddings and dimensionality reduction techniques.