32 citations · 63 across the 15 of their papers we have counts for
15 papers
EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion
Guangyao Zhai, Evin Pınar Örnek, Dave Zhenyu Chen +5
We present EchoScene, an interactive and controllable generative model that generates 3D indoor scenes on scene graphs. EchoScene leverages a dual-branch diffusion model that dynam…
FoundPose: Unseen Object Pose Estimation with Foundation Features
Evin Pınar Örnek, Yann Labbé, Bugra Tekin +4
We propose FoundPose, a model-based method for 6D pose estimation of unseen objects from a single RGB image. The method can quickly onboard new objects using their 3D models withou…
CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion
Guangyao Zhai, Evin Pınar Örnek, Shun-Cheng Wu +4
Controllable scene synthesis aims to create interactive environments for various industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applicat…
SupeRGB-D: Zero-shot Instance Segmentation in Cluttered Indoor Environments
Evin Pınar Örnek, Aravindhan K Krishnan, Shreekant Gayaka +4
Object instance segmentation is a key challenge for indoor robots navigating cluttered environments with many small objects. Limitations in 3D sensing capabilities often make it di…
LatentSwap3D: Semantic Edits on 3D Image GANs
Enis Simsar, Alessio Tonioni, Evin Pınar Örnek +1
3D GANs have the ability to generate latent codes for entire 3D volumes rather than only 2D images. These models offer desirable features like high-quality geometry and multi-view…
4D-OR: Semantic Scene Graphs for OR Domain Modeling
Ege Özsoy, Evin Pınar Örnek, Ulrich Eck +3
Surgical procedures are conducted in highly complex operating rooms (OR), comprising different actors, devices, and interactions. To date, only medically trained human experts are…
From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction
Evin Pınar Örnek, Shristi Mudgal, Johanna Wald +3
There have been numerous recently proposed methods for monocular depth prediction (MDP) coupled with the equally rapid evolution of benchmarking tools. However, we argue that MDP i…
Object-aware Monocular Depth Prediction with Instance Convolutions
Enis Simsar, Evin Pınar Örnek, Fabian Manhardt +3
With the advent of deep learning, estimating depth from a single RGB image has recently received a lot of attention, being capable of empowering many different applications ranging…
3D Compositional Zero-shot Learning with DeCompositional Consensus
Muhammad Ferjad Naeem, Evin Pınar Örnek, Yongqin Xian +2
Parts represent a basic unit of geometric and semantic similarity across different objects. We argue that part knowledge should be composable beyond the observed object classes. To…
Multimodal Semantic Scene Graphs for Holistic Modeling of Surgical Procedures
Ege Özsoy, Evin Pınar Örnek, Ulrich Eck +2
From a computer science viewpoint, a surgical domain model needs to be a conceptual one incorporating both behavior and data. It should therefore model actors, devices, tools, thei…
Co-Planar Parametrization for Stereo-SLAM and Visual-Inertial Odometry
Xin Li, Yanyan Li, Evin Pınar Örnek +2
This work proposes a novel SLAM framework for stereo and visual inertial odometry estimation. It builds an efficient and robust parametrization of co-planar points and lines which…
Zero-Shot Activity Recognition with Videos
Evin Pinar Ornek
In this paper, we examined the zero-shot activity recognition task with the usage of videos. We introduce an auto-encoder based model to construct a multimodal joint embedding spac…
ModelHub.AI: Dissemination Platform for Deep Learning Models
Ahmed Hosny, Michael Schwier, Christoph Berger +13
Recent advances in artificial intelligence research have led to a profusion of studies that apply deep learning to problems in image analysis and natural language processing among…
Magnetic-Visual Sensor Fusion-based Dense 3D Reconstruction and Localization for Endoscopic Capsule Robots
Mehmet Turan, Yasin Almalioglu, Evin Pinar Ornek +3
Reliable and real-time 3D reconstruction and localization functionality is a crucial prerequisite for the navigation of actively controlled capsule endoscopic robots as an emerging…
Unsupervised Odometry and Depth Learning for Endoscopic Capsule Robots
Mehmet Turan, Evin Pinar Ornek, Nail Ibrahimli +4
In the last decade, many medical companies and research groups have tried to convert passive capsule endoscopes as an emerging and minimally invasive diagnostic technology into act…