Mehmet Ozgur Turkoglu

LoRA-Ensemble. LoRA-Ensemble: Efficient Uncertainty Modelling for Self-attention Networks

MedSAM. Segment Anything in Medical Images

AutoSAM. finetuning SAM with non-promptable decoder on medical images

opentryon. Open-source APIs, SDKs, and models for building virtual try-on and fashion AI applications. Generate models, edit garments, create photoshoots, and build personalized fashion experiences.

ECON. [CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration

InstantAvatar. InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds (CVPR 2023)

vid2avatar. Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition (CVPR2023)

Subject-Diffusion. Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning

ladi-vton. [ACM MM 2023] - LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On

e4t-diffusion. Implementation of Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models

langchain. The agent engineering platform.

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

ImageBind. ImageBind One Embedding Space to Bind Them All

lmql. A language for constraint-guided and efficient LLM programming.

AICommand. ChatGPT integration with Unity Editor

InST. Official implementation of the paper “Inversion-Based Style Transfer with Diffusion Models” (CVPR 2023)

torchview. torchview: visualize pytorch models

interp_ensembles. Python

voxgraf. Official code release for VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids

FILM-Ensemble. [NeurIPS 2022] FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation

nerfstudio. A collaboration friendly studio for NeRFs

guided-inpainting. Towards Unified Keyframe Propagation Models

slidev. Presentation Slides for Developers

MODNet. A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

guided-diffusion. Python

torchshow. Visualize PyTorch tensors with a single line of code.

relpose-gnn. [3DV21] Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision, M. Türkoǧlu et al.

latent-pose-reenactment. The authors' implementation of the "Neural Head Reenactment with Latent Pose Descriptors" (CVPR 2020) paper.

awesome-face-generation. Basic GAN frameworks and approaches for face swap, reenactment, and stylizing.

PyTorch-Model-Compare. Compare neural networks by their feature similarity

L2M-GAN. Python

TaskRouting. (ICCV 2019 Oral) Many Task Learning With Task Routing http://openaccess.thecvf.com/content_ICCV_2019/html/Strezoski_Many_Task_Learning_With_Task_Routing_ICCV_2019_paper.html

demucs. Code for the paper Hybrid Spectrogram and Waveform Source Separation

NeuralCDEcrops. Repository for my master thesis at EPFL: "Neural controlled differential equations for crop classification"

Merlion. Merlion: A Machine Learning Framework for Time Series Intelligence

st_tau. This repository contains code for the paper "Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs" (Wang, Lawrence & Niepert, ICLR 2021).

uncertainty-toolbox. Uncertainty Toolbox: a Python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization

pytorch_geometric_temporal. PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)

edward2. A simple probabilistic programming language.

multi-stage-convSTAR-network. [RSE 2021] Crop mapping from image time series: deep learning with multi-scale label hierarchies

tf_star_rnn. Tensorflow 2.0 implementation of STAR RNN

STAR_Network_Pytorch. Pytorch Implementation of the STAckable Recurrent Network

temperature_scaling. A simple way to calibrate your neural network.

visloc-relapose. A 2D Visual Localization Framework based on Essential Matrices [ICRA2020]

FasterNeuralDiffEq. Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)

lightweight-temporal-attention-pytorch. A PyTorch implementation of the Light Temporal Attention Encoder (L-TAE) for satellite image time series. classification

kNN-CUDA. Fast k nearest neighbor search using GPU

ODEcrop. [TGRS21] Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations

tsdf-fusion-python. Python code to fuse multiple RGB-D images into a TSDF voxel volume.

big_transfer. Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.

wide-resnet.pytorch. Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch

ONI. PyTorch and Torch implementation for our accepted CVPR 2020 paper (Oral): Controllable Orthogonalization in Training DNNs

nonnormal-init. Sequential non-normal initializers for recurrent neural networks

SlowFast. PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

B-CNN. Sample code of B-CNN paper (https://arxiv.org/abs/1709.09890) written in Python3+.

imbalanced-dataset-sampler. A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.

HiLAP. Code for paper "Hierarchical Text Classification with Reinforced Label Assignment" EMNLP 2019

lucid. A collection of infrastructure and tools for research in neural network interpretability.

CropDetectionDL. Python

NRU. Python

STAckable-Recurrent-network. [PAMI 2021] Gating Revisited: Deep Multi-layer RNNs That Can Be Trained

mean-field-theory-deep-learning. paper lists and information on mean-field theory of deep learning

conv-tt-lstm. Python

RecurrentHighwayNetworks. Recurrent Highway Networks - Implementations for Tensorflow, Torch7, Theano and Brainstorm

bnlstm. Batch normalized LSTM for tensorflow

Truncated_SVD_for_Image_Compression. Matlab code for SVD-based image compression

Lane_Tracking_using_Particle_Filters. Particle filter-based lane tracking Matlab code

e3d_lstm. e3d-lstm; Eidetic 3D LSTM A Model for Video Prediction and Beyond

latent_ode. Code for "Latent ODEs for Irregularly-Sampled Time Series" paper

crop-type-mapping. Crop type mapping of small holder farms in Ghana, and South Sudan

ms-tcn. Python

DeepVO-pytorch. PyTorch Implementation of DeepVO

kornia. 🐍 Geometric Computer Vision Library for Spatial AI

DTPP. Deep networks with Temporal Pyramid Pooling. The official implementation for "End-to-end Video-level Representation Learning for Action Recognition, ICPR 2018."

Action-Recognition. Exploration of different solutions to action recognition in video, using neural networks implemented in PyTorch.

pyflow. Fast, accurate and easy to run dense optical flow with python wrapper

tutorials. Jupyter Notebook

BreizhCrops. A Satellite Time Series Dataset for Crop Type Identification

TemporalConvolutionalNetworks. Python

keras-tcn. Keras Temporal Convolutional Network. Supports Python and R.

3D_face_reconstruction_from_stereo_pairs. Matlab code for 3D face reconstruction from stereo image pairs

cnn_graph. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

dntm. D-NTM paper repo

fieldRNN. Temporal Vegetation Classification with Recurrent Neural Networks

SphereNet-pytorch. Python

Sequential-Scene-GAN. [AAAI 2019] A Layer-Based Sequential Framework for Scene Generation with GANs

cubenet. 3D Roto-translation equivariant convolutions

torchdiffeq. Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

Neural-Ordinary-Differential-Equations. Sample implementation of Neural Ordinary Differential Equations

PlotNeuralNet. Latex code for making neural networks diagrams

pytorch-fid. Compute FID scores with PyTorch.

sngan_projection. GANs with spectral normalization and projection discriminator

StackGAN-Pytorch. Python

lr-gan.pytorch. Pytorch code for our ICLR 2017 paper "Layered-Recursive GAN for image generation"

really-awesome-gan. A list of papers on Generative Adversarial (Neural) Networks

action-recognition-using-3d-resnet. Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.

pix2pixHD. Synthesizing and manipulating 2048x1024 images with conditional GANs