[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning
-
Updated
Sep 9, 2024 - Jupyter Notebook
[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning
A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation
Re-identify animals from cam trap images
[CVPR'24] NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild
AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2
This repository contains the code implementation used in the paper: "Human-in-the-Loop Segmentation of Multi-species Coral Imagery".
[ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
Image Classification with DINOv2
The official source code of paper in ECCV 2024. "Aligning Neuronal Coding of Dynamic Visual Scenes with Foundation Vision Models"
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.
Implementation of Fréchet Distance with DINOv2 backbone in Pytorch.
Official implementation of the paper 'Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery'
Clustering images of skin diseases using DINOv2 embeddings and dimensionality reduction techniques.
Framework for learning multi-domain image embeddings suitable for multi-domain image retrieval at instance-level
DepthArt: From Snapshot to Landscape
Code for my Master's Thesis "Deep Neural Encoding Models of the Human Visual Cortex to Predict fMRI Responses to Natural Visual Scenes" and my submission for the "Algonauts Project 2023 Challenge".
This is a warehouse for DinoV2-models, based pytorch framework.
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.
Add a description, image, and links to the dinov2 topic page so that developers can more easily learn about it.
To associate your repository with the dinov2 topic, visit your repo's landing page and select "manage topics."