Search Results for author: Sezer Karaoglu

Found 29 papers, 11 papers with code

Joint 3D Layout and Depth Prediction from a Single Indoor Panorama Image

no code implementations ECCV 2020 Wei Zeng, Sezer Karaoglu, Theo Gevers

Leveraging the layout depth map as an intermediate representation, our proposed method outperforms existing methods for both panorama layout prediction and depth estimation.

Depth Estimation Depth Prediction

LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting

no code implementations29 Nov 2024 Xiaoyan Xing, Konrad Groh, Sezer Karaoglu, Theo Gevers, Anand Bhattad

Our approach makes two key contributions: a data curation strategy from the StyleGAN-based relighting model for our training, and a modified diffusion-based ControlNet that processes both latent intrinsic properties from the source image and latent extrinsic properties from the target image.

FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training

no code implementations4 Nov 2024 Ruihong Yin, Vladimir Yugay, Yue Li, Sezer Karaoglu, Theo Gevers

To address this, we present a 3D Gaussian-based novel view synthesis method using sparse input images that can accurately render the scene from the viewpoints not covered by the training images.

Depth Estimation NeRF +1

RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Models

no code implementations16 Sep 2024 Başak Melis Öcal, Maxim Tatarchenko, Sezer Karaoglu, Theo Gevers

Specifically, RealDiff simulates a diffusion process at the missing object parts while conditioning the generation on the partial input to address the multimodal nature of the task.

Object Point Cloud Completion

Ray-Distance Volume Rendering for Neural Scene Reconstruction

no code implementations28 Aug 2024 Ruihong Yin, Yunlu Chen, Sezer Karaoglu, Theo Gevers

To tackle this issue, our work proposes a novel approach for indoor scene reconstruction, which instead parameterizes the density function with the Signed Ray Distance Function (SRDF).

3D geometry Indoor Scene Reconstruction

SceneTeller: Language-to-3D Scene Generation

no code implementations30 Jul 2024 Başak Melis Öcal, Maxim Tatarchenko, Sezer Karaoglu, Theo Gevers

Designing high-quality indoor 3D scenes is important in many practical applications, such as room planning or game development.

In-Context Learning Scene Generation

Retinex-Diffusion: On Controlling Illumination Conditions in Diffusion Models via Retinex Theory

no code implementations29 Jul 2024 Xiaoyan Xing, Vincent Tao Hu, Jan Hendrik Metzen, Konrad Groh, Sezer Karaoglu, Theo Gevers

This paper introduces a novel approach to illumination manipulation in diffusion models, addressing the gap in conditional image generation with a focus on lighting conditions.

Conditional Image Generation

Relational Prior Knowledge Graphs for Detection and Instance Segmentation

1 code implementation11 Oct 2023 Osman Ülger, Yu Wang, Ysbrand Galama, Sezer Karaoglu, Theo Gevers, Martin R. Oswald

Humans have a remarkable ability to perceive and reason about the world around them by understanding the relationships between objects.

Instance Segmentation Knowledge Graphs +5

Intrinsic Image Decomposition Using Point Cloud Representation

1 code implementation20 Jul 2023 Xiaoyan Xing, Konrad Groh, Sezer Karaoglu, Theo Gevers

The purpose of intrinsic decomposition is to separate an image into its albedo (reflective properties) and shading components (illumination properties).

Intrinsic Image Decomposition

SIGNet: Intrinsic Image Decomposition by a Semantic and Invariant Gradient Driven Network for Indoor Scenes

1 code implementation30 Aug 2022 Partha Das, Sezer Karaoglu, Arjan Gijsenij, Theo Gevers

An ablation study is conducted showing that the use of the proposed priors and progressive CNN increase the IID performance.

Intrinsic Image Decomposition

Multi-person 3D pose estimation from a single image captured by a fisheye camera

no code implementations Computer Vision and Image Understanding 2022 YaHui Zhang, ShaoDi You, Sezer Karaoglu, Theo Gevers

Multi-person 3D pose estimation with absolute depths for a fisheye camera is a challenging task but with valuable applications in daily life, especially for video surveillance.

3D Human Pose Estimation 3D Pose Estimation

PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition

1 code implementation CVPR 2022 Partha Das, Sezer Karaoglu, Theo Gevers

An extensive ablation study and large scale experiments are conducted showing that it is beneficial for edge-driven hybrid IID networks to make use of illumination invariant descriptors and that separating global and local cues helps in improving the performance of the network.

Intrinsic Image Decomposition

Spatio-temporal Features for Generalized Detection of Deepfake Videos

no code implementations22 Oct 2020 Ipek Ganiyusufoglu, L. Minh Ngô, Nedko Savov, Sezer Karaoglu, Theo Gevers

In this paper, we empirically show that existing approaches on image and sequence classifiers generalize poorly to new manipulation techniques.

DeepFake Detection Face Swapping

Multi-Loss Weighting with Coefficient of Variations

1 code implementation3 Sep 2020 Rick Groenendijk, Sezer Karaoglu, Theo Gevers, Thomas Mensink

In this paper, we propose a weighting scheme based on the coefficient of variations and set the weights based on properties observed while training the model.

Monocular Depth Estimation Multi-Task Learning +1

Physics-based Shading Reconstruction for Intrinsic Image Decomposition

no code implementations3 Sep 2020 Anil S. Baslamisli, Yang Liu, Sezer Karaoglu, Theo Gevers

We investigate the use of photometric invariance and deep learning to compute intrinsic images (albedo and shading).

Intrinsic Image Decomposition

Kinship Identification through Joint Learning Using Kinship Verification Ensembles

1 code implementation ECCV 2020 Wei Wang, ShaoDi You, Sezer Karaoglu, Theo Gevers

The experiments further show significant performance improvement of kinship verification when trained on the same dataset with more realistic distributions.

Kinship Verification

On the Benefit of Adversarial Training for Monocular Depth Estimation

1 code implementation29 Oct 2019 Rick Groenendijk, Sezer Karaoglu, Theo Gevers, Thomas Mensink

For the quality of the image reconstruction and disparity prediction, a combination of different losses is used, including L1 image reconstruction losses and left-right disparity smoothness.

Depth Prediction Generative Adversarial Network +2

Improving Face Detection Performance with 3D-Rendered Synthetic Data

no code implementations18 Dec 2018 Jian Han, Sezer Karaoglu, Hoang-An Le, Theo Gevers

In this paper, we provide a synthetic data generator methodology with fully controlled, multifaceted variations based on a new 3D face dataset (3DU-Face).

Data Augmentation Face Detection

Color Constancy by GANs: An Experimental Survey

no code implementations7 Dec 2018 Partha Das, Anil S. Baslamisli, Yang Liu, Sezer Karaoglu, Theo Gevers

In this paper, we formulate the color constancy task as an image-to-image translation problem using GANs.

Color Constancy Image-to-Image Translation +2

Automatic Generation of Dense Non-rigid Optical Flow

1 code implementation5 Dec 2018 Hoàng-Ân Lê, Tushar Nimbhorkar, Thomas Mensink, Anil S. Baslamisli, Sezer Karaoglu, Theo Gevers

There hardly exists any large-scale datasets with dense optical flow of non-rigid motion from real-world imagery as of today.

Optical Flow Estimation

Detect2Rank : Combining Object Detectors Using Learning to Rank

no code implementations26 Dec 2014 Sezer Karaoglu, Yang Liu, Theo Gevers

Experiments on the PASCAL VOC07 and VOC10 datasets show that the proposed method significantly outperforms single object detectors, DPM (8. 4%), CN (6. 8%) and EES (17. 0%) on VOC07 and DPM (6. 5%), CN (5. 5%) and EES (16. 2%) on VOC10.

Learning-To-Rank Object +2

Cannot find the paper you are looking for? You can Submit a new open access paper.