Sezer Karaoğlu
YOU?
Author Swipe
View article: LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting
LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting Open
We introduce LumiNet, a novel architecture that leverages generative models and latent intrinsic representations for effective lighting transfer. Given a source image and a target lighting image, LumiNet synthesizes a relit version of the …
View article: FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training Open
The field of novel view synthesis from images has seen rapid advancements with the introduction of Neural Radiance Fields (NeRF) and more recently with 3D Gaussian Splatting. Gaussian Splatting became widely adopted due to its efficiency a…
View article: RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Models
RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Models Open
Point cloud completion aims to recover the complete 3D shape of an object from partial observations. While approaches relying on synthetic shape priors achieved promising results in this domain, their applicability and generalizability to …
View article: Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstruction
Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstruction Open
In addition to color and textural information, geometry provides important cues for 3D scene reconstruction. However, current reconstruction methods only include geometry at the feature level thus not fully exploiting the geometric informa…
View article: Ray-Distance Volume Rendering for Neural Scene Reconstruction
Ray-Distance Volume Rendering for Neural Scene Reconstruction Open
Existing methods in neural scene reconstruction utilize the Signed Distance Function (SDF) to model the density function. However, in indoor scenes, the density computed from the SDF for a sampled point may not consistently reflect its rea…
View article: Image semantic segmentation of indoor scenes: A survey
Image semantic segmentation of indoor scenes: A survey Open
This survey provides a comprehensive evaluation of various deep learning-based segmentation architectures. It covers a wide range of models, from traditional ones like FCN and PSPNet to more modern approaches like SegFormer and FAN. In add…
View article: SceneTeller: Language-to-3D Scene Generation
SceneTeller: Language-to-3D Scene Generation Open
Designing high-quality indoor 3D scenes is important in many practical applications, such as room planning or game development. Conventionally, this has been a time-consuming process which requires both artistic skill and familiarity with …
View article: Retinex-Diffusion: On Controlling Illumination Conditions in Diffusion Models via Retinex Theory
Retinex-Diffusion: On Controlling Illumination Conditions in Diffusion Models via Retinex Theory Open
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. We conceptualize the diffusion model as a black-box image rend…
View article: Relational Prior Knowledge Graphs for Detection and Instance Segmentation
Relational Prior Knowledge Graphs for Detection and Instance Segmentation Open
Humans have a remarkable ability to perceive and reason about the world around them by understanding the relationships between objects. In this paper, we investigate the effectiveness of using such relationships for object detection and in…
View article: Intrinsic Image Decomposition Using Point Cloud Representation
Intrinsic Image Decomposition Using Point Cloud Representation Open
The purpose of intrinsic decomposition is to separate an image into its albedo (reflective properties) and shading components (illumination properties). This is challenging because it's an ill-posed problem. Conventional approaches primari…
View article: Corrigendum: Initial development of perpetrator confrontation using deepfake technology in victims with sexual violence-related PTSD and moral injury
Corrigendum: Initial development of perpetrator confrontation using deepfake technology in victims with sexual violence-related PTSD and moral injury Open
[This corrects the article DOI: 10.3389/fpsyt.2022.882957.].
View article: SIGNet: Intrinsic Image Decomposition by a Semantic and Invariant Gradient Driven Network for Indoor Scenes
SIGNet: Intrinsic Image Decomposition by a Semantic and Invariant Gradient Driven Network for Indoor Scenes Open
Intrinsic image decomposition (IID) is an under-constrained problem. Therefore, traditional approaches use hand crafted priors to constrain the problem. However, these constraints are limited when coping with complex scenes. Deep learning-…
View article: Intrinsic image decomposition using physics-based cues and CNNs
Intrinsic image decomposition using physics-based cues and CNNs Open
Intrinsic image decomposition is the decomposition of an image into its reflectance and shading components. The intrinsic image decomposition problem is inherently ill-posed, since there can be multiple solutions to compute the intrinsic c…
View article: Initial development of perpetrator confrontation using deepfake technology in victims with sexual violence-related PTSD and moral injury
Initial development of perpetrator confrontation using deepfake technology in victims with sexual violence-related PTSD and moral injury Open
Background Interventions aimed at easing negative moral (social) emotions and restoring social bonds – such as amend-making and forgiving—have a prominent role in the treatment of moral injury. As real-life contact between persons involved…
View article: Multi-person 3D pose estimation from a single image captured by a fisheye camera
Multi-person 3D pose estimation from a single image captured by a fisheye camera Open
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. However, to the best of our knowledge, such problem has not be…
View article: PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition
PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition Open
Intrinsic image decomposition is the process of recovering the image formation components (reflectance and shading) from an image. Previous methods employ either explicit priors to constrain the problem or implicit constraints as formulate…
View article: Generative Models for Multi-Illumination Color Constancy
Generative Models for Multi-Illumination Color Constancy Open
In this paper, the aim is multi-illumination color constancy. However, most of the existing color constancy methods are designed for single light sources. Furthermore, datasets for learning multiple illumination color constancy are largely…
View article: Automatic generation of dense non-rigid optical flow
Automatic generation of dense non-rigid optical flow Open
There hardly exists any large-scale datasets with dense optical flow of non-rigid motion from real-world imagery as of today. The reason lies mainly in the required setup to derive ground truth optical flows: a series of images with known …
View article: ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition
ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition Open
In general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in d…
View article: Physics-based shading reconstruction for intrinsic image decomposition
Physics-based shading reconstruction for intrinsic image decomposition Open
We investigate the use of photometric invariance and deep learning to compute intrinsic images (albedo and shading). We propose albedo and shading gradient descriptors which are derived from physics-based models. Using the descriptors, alb…
View article: Multi-Loss Weighting with Coefficient of Variations
Multi-Loss Weighting with Coefficient of Variations Open
Many interesting tasks in machine learning and computer vision are learned by optimising an objective function defined as a weighted linear combination of multiple losses. The final performance is sensitive to choosing the correct (relativ…
View article: EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes
EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes Open
Multimodal large-scale datasets for outdoor scenes are mostly designed for urban driving problems. The scenes are highly structured and semantically different from scenarios seen in nature-centered scenes such as gardens or parks. To promo…
View article: Spatio-temporal Features for Generalized Detection of Deepfake Videos
Spatio-temporal Features for Generalized Detection of Deepfake Videos Open
For deepfake detection, video-level detectors have not been explored as extensively as image-level detectors, which do not exploit temporal data. In this paper, we empirically show that existing approaches on image and sequence classifiers…
View article: Kinship Identification through Joint Learning Using Kinship Verification Ensembles
Kinship Identification through Joint Learning Using Kinship Verification Ensembles Open
Kinship verification is a well-explored task: identifying whether or not two persons are kin. In contrast, kinship identification has been largely ignored so far. Kinship identification aims to further identify the particular type of kinsh…
View article: Three-D Wide Faces (3DWF): Facial Landmark Detection and 3D Reconstruction over a New RGB–D Multi-Camera Dataset
Three-D Wide Faces (3DWF): Facial Landmark Detection and 3D Reconstruction over a New RGB–D Multi-Camera Dataset Open
Latest advances of deep learning paradigm and 3D imaging systems have raised the necessity for more complete datasets that allow exploitation of facial features such as pose, gender or age. In our work, we propose a new facial dataset coll…