YalimD
Ph.D. student at Bilkent University. Focuses on computer graphics, vision and deep learning.
Bilkent UniversityAnkara
Pinned Repositories
motion-transfer-personality
This work analyzes the influence of movement and appearance on the perceived personality of short videos altered by motion transfer networks.
Artificial-Crowd
Generating Artificial Agents over Projected Agents from Video Feed for Crowd Simulation
augmentation_of_pedestrians_over_videos
This project aims to augment a virtual crowd into a real one extracted from given video. The project is written on Unity using C#.
bw_contour_to_2d_mesh
Generates a mesh from a binary image using OpenCV contours and Triangle library
image_shadow_remover
Implementation of Shadow Removal Algorithms
navigable_area_reconstruction_from_image
Given an input image taken from a survaillance-alike video and pedestrian detection data, tries to calculate the perspective correction operation that rectifies the navigable area in the image. The rectified image represents the blueprint (map) of the navigable regions.
Point-Cloud-Registration-With-Quantile-Assignment
We refined the quantile assignment algorithm by integrating prevalent feature descriptors and transformation estimation methods to enhance the correspondence between the source and target point clouds.
YalimD's Repositories
YalimD/image_shadow_remover
Implementation of Shadow Removal Algorithms
YalimD/bw_contour_to_2d_mesh
Generates a mesh from a binary image using OpenCV contours and Triangle library
YalimD/Artificial-Crowd
Generating Artificial Agents over Projected Agents from Video Feed for Crowd Simulation
YalimD/augmentation_of_pedestrians_over_videos
This project aims to augment a virtual crowd into a real one extracted from given video. The project is written on Unity using C#.
YalimD/Point-Cloud-Registration-With-Quantile-Assignment
We refined the quantile assignment algorithm by integrating prevalent feature descriptors and transformation estimation methods to enhance the correspondence between the source and target point clouds.
YalimD/auto_segmented_navigable_area_extraction
Given input video and MOT compatible pedestrian tracking data, determines the navigable regions in the video using deep learning based segmentation techniques.
YalimD/navigable_area_reconstruction_from_image
Given an input image taken from a survaillance-alike video and pedestrian detection data, tries to calculate the perspective correction operation that rectifies the navigable area in the image. The rectified image represents the blueprint (map) of the navigable regions.
YalimD/pedestrian_tracking
Given an input video, detects pedestrians using either HOG (Histogram of Oriented Gradients) or R-CNN's. For performance reasons, only searches regions where movement occurs, using background subtraction.
YalimD/AI-Labs-Joint-Program
Repository for inzva AI Labs Joint Program
YalimD/aitviewer
A set of tools to visualize and interact with sequences of 3D data.
YalimD/animation-utils
YalimD/awesome
:sunglasses: Curated list of awesome lists
YalimD/cri
Moved to https://github.com/containerd/containerd/tree/master/pkg/cri . If you wish to submit issues/PRs, please submit to https://github.com/containerd/containerd
YalimD/CS554Project
Play
YalimD/FCGF_QuantileEdition
YalimD/fluentd-kubernetes-daemonset
Fluentd daemonset for Kubernetes and it Docker image
YalimD/frankmocap
A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
YalimD/game-programmer
A Study Path for Game Programmer
YalimD/GH-ICP
GH-ICP: Iterative Closest Point algorithm with global optimal matching and hybrid metric [3DV' 18]
YalimD/HyperDiffusion
Official code repository of "HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion" @ ICCV 2023
YalimD/ihoi
YalimD/MapsModelsImporter
A Blender add-on to import models from google maps
YalimD/opencv
Open Source Computer Vision Library
YalimD/PIXIE
YalimD/Rakosi.github.io
My Personal Website Content
YalimD/rke2
YalimD/roop
one-click deepfake (face swap)
YalimD/tensorflow
Computation using data flow graphs for scalable machine learning
YalimD/Thin-Plate-Spline-Motion-Model
[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.
YalimD/YalimD