Search Results for author: Slobodan Ilic

Found 52 papers, 12 papers with code

Multi-Forest Tracker: A Chameleon in Tracking

no code implementations CVPR 2014 David J. Tan, Slobodan Ilic

Moreover, it demonstrates robustness to strong illumination changes when tracking templates using intensity images, and robustness in tracking 3D objects from arbitrary viewpoints even in the presence of motion blur that causes missing or erroneous data in depth images.

Object Tracking

Human Shape and Pose Tracking Using Keyframes

no code implementations CVPR 2014 Chun-Hao Huang, Edmond Boyer, Nassir Navab, Slobodan Ilic

In contrast to many existing approaches that rely on a single reference model, multiple templates represent a larger variability of human poses.

Pose Tracking

Multiple human pose estimation with temporally consistent 3d pictorial structures

no code implementations6 Sep 2014 Vasileios Belagiannis, Xinchao Wang, Bernt Schiele, Pascal Fua, Slobodan Ilic, Nassir Navab

To address these challenges, we propose a temporally consistent 3D Pictorial Structures model (3DPS) for multiple human pose estimation from multiple camera views.

3D Multi-Person Pose Estimation 3D Pose Estimation

Toward User-Specific Tracking by Detection of Human Shapes in Multi-Cameras

no code implementations CVPR 2015 Chun-Hao Huang, Edmond Boyer, Bibiana do Canto Angonese, Nassir Navab, Slobodan Ilic

It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences.

Temporal Sequences

A Versatile Learning-Based 3D Temporal Tracker: Scalable, Robust, Online

no code implementations ICCV 2015 David Joseph Tan, Federico Tombari, Slobodan Ilic, Nassir Navab

This paper proposes a temporal tracking algorithm based on Random Forest that uses depth images to estimate and track the 3D pose of a rigid object in real-time.

Occlusion Handling

Dominant Codewords Selection with Topic Model for Action Recognition

no code implementations1 May 2016 Hirokatsu Kataoka, Masaki Hayashi, Kenji Iwata, Yutaka Satoh, Yoshimitsu Aoki, Slobodan Ilic

Latent Dirichlet allocation (LDA) is used to develop approximations of human motion primitives; these are mid-level representations, and they adaptively integrate dominant vectors when classifying human activities.

Action Recognition Temporal Action Localization

Volumetric 3D Tracking by Detection

no code implementations CVPR 2016 Chun-Hao Huang, Benjamin Allain, Jean-Sebastien Franco, Nassir Navab, Slobodan Ilic, Edmond Boyer

In this paper, we propose a new framework for 3D tracking by detection based on fully volumetric representations.

Computational Efficiency

An Octree-Based Approach towards Efficient Variational Range Data Fusion

no code implementations26 Aug 2016 Wadim Kehl, Tobias Holl, Federico Tombari, Slobodan Ilic, Nassir Navab

Volume-based reconstruction is usually expensive both in terms of memory consumption and runtime.

CAD Priors for Accurate and Flexible Instance Reconstruction

no code implementations ICCV 2017 Tolga Birdal, Slobodan Ilic

With aid of this prior acting as a proxy, we propose a fully enhanced pipeline, capable of automatically detecting and segmenting the object of interest from scenes and creating a pose graph, online, with linear complexity.

3D Reconstruction Novel Object Detection +3

KillingFusion: Non-Rigid 3D Reconstruction Without Correspondences

no code implementations CVPR 2017 Miroslava Slavcheva, Maximilian Baust, Daniel Cremers, Slobodan Ilic

We introduce a geometry-driven approach for real-time 3D reconstruction of deforming surfaces from a single RGB-D stream without any templates or shape priors.

3D Reconstruction Unity

PPFNet: Global Context Aware Local Features for Robust 3D Point Matching

1 code implementation CVPR 2018 Haowen Deng, Tolga Birdal, Slobodan Ilic

We present PPFNet - Point Pair Feature NETwork for deeply learning a globally informed 3D local feature descriptor to find correspondences in unorganized point clouds.

Point Cloud Registration

A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds

no code implementations CVPR 2018 Tolga Birdal, Benjamin Busam, Nassir Navab, Slobodan Ilic, Peter Sturm

As opposed to state-of-the-art, where a tailored algorithm treats each primitive type separately, we propose to encapsulate all types in a single robust detection procedure.

Scene Understanding

Keep it Unreal: Bridging the Realism Gap for 2.5D Recognition with Geometry Priors Only

no code implementations24 Apr 2018 Sergey Zakharov, Benjamin Planche, Ziyan Wu, Andreas Hutter, Harald Kosch, Slobodan Ilic

With the increasing availability of large databases of 3D CAD models, depth-based recognition methods can be trained on an uncountable number of synthetically rendered images.

Generative Adversarial Network

When Regression Meets Manifold Learning for Object Recognition and Pose Estimation

no code implementations16 May 2018 Mai Bui, Sergey Zakharov, Shadi Albarqouni, Slobodan Ilic, Nassir Navab

By combining the strengths of manifold learning using triplet loss and pose regression, we could either estimate the pose directly reducing the complexity compared to NN search, or use learned descriptor for the NN descriptor matching.

Multi-Task Learning Object Recognition +4

Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC

no code implementations NeurIPS 2018 Tolga Birdal, Umut Şimşekli, M. Onur Eken, Slobodan Ilic

We introduce Tempered Geodesic Markov Chain Monte Carlo (TG-MCMC) algorithm for initializing pose graph optimization problems, arising in various scenarios such as SFM (structure from motion) or SLAM (simultaneous localization and mapping).

Simultaneous Localization and Mapping

SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-Rigid Motion

no code implementations CVPR 2018 Miroslava Slavcheva, Maximilian Baust, Slobodan Ilic

We present a system that builds 3D models of non-rigidly moving surfaces from scratch in real time using a single RGB-D stream.

3D Reconstruction

Survey of Higher Order Rigid Body Motion Interpolation Methods for Keyframe Animation and Continuous-Time Trajectory Estimation

no code implementations 3D Vision 2018 2018 Adrian Haarbach, Tolga Birdal, Slobodan Ilic

In this survey we carefully analyze the characteristics of higher order rigid body motion interpolation methods to obtain a continuous trajectory from a discrete set of poses.

Motion Interpolation

Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition

no code implementations9 Oct 2018 Benjamin Planche, Sergey Zakharov, Ziyan Wu, Andreas Hutter, Harald Kosch, Slobodan Ilic

Applying our approach to object recognition from texture-less CAD data, we present a custom generative network which fully utilizes the purely geometrical information to learn robust features and achieve a more refined mapping for unseen color images.

Denoising Domain Adaptation +1

Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits

no code implementations4 Jan 2019 Tolga Birdal, Benjamin Busam, Nassir Navab, Slobodan Ilic, Peter Sturm

Based upon the idea of aligning the quadric gradients with the surface normals, our first formulation is exact and requires as low as four oriented points.

DPOD: 6D Pose Object Detector and Refiner

2 code implementations ICCV 2019 Sergey Zakharov, Ivan Shugurov, Slobodan Ilic

An additional RGB pose refinement of the initial pose estimates is performed using a custom deep learning-based refinement scheme.

3D Object Detection 6D Pose Estimation +3

Adversarial Networks for Camera Pose Regression and Refinement

no code implementations15 Mar 2019 Mai Bui, Christoph Baur, Nassir Navab, Slobodan Ilic, Shadi Albarqouni

Despite recent advances on the topic of direct camera pose regression using neural networks, accurately estimating the camera pose of a single RGB image still remains a challenging task.

Pose Estimation regression

HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects

no code implementations5 Apr 2019 Roman Kaskman, Sergey Zakharov, Ivan Shugurov, Slobodan Ilic

We also present a set of benchmarks to test various desired detector properties, particularly focusing on scalability with respect to the number of objects and resistance to changing light conditions, occlusions and clutter.

6D Pose Estimation 6D Pose Estimation using RGB +1

3D Local Features for Direct Pairwise Registration

no code implementations CVPR 2019 Haowen Deng, Tolga Birdal, Slobodan Ilic

Our extensive quantitative and qualitative experiments suggests that our approach outperforms the state of the art in challenging real datasets of pairwise registration and that augmenting the keypoints with local pose information leads to better generalization and a dramatic speed-up.

Pose Estimation

3D Object Instance Recognition and Pose Estimation Using Triplet Loss with Dynamic Margin

no code implementations9 Apr 2019 Sergey Zakharov, Wadim Kehl, Benjamin Planche, Andreas Hutter, Slobodan Ilic

In this paper, we address the problem of 3D object instance recognition and pose estimation of localized objects in cluttered environments using convolutional neural networks.

Pose Estimation

On Object Symmetries and 6D Pose Estimation from Images

no code implementations20 Aug 2019 Giorgia Pitteri, Michaël Ramamonjisoa, Slobodan Ilic, Vincent Lepetit

Objects with symmetries are common in our daily life and in industrial contexts, but are often ignored in the recent literature on 6D pose estimation from images.

6D Pose Estimation Object

CorNet: Generic 3D Corners for 6D Pose Estimation of New Objects without Retraining

no code implementations29 Aug 2019 Giorgia Pitteri, Slobodan Ilic, Vincent Lepetit

We first learn to detect object corners of various shapes in images and also to predict their 3D poses, by using training images of a small set of objects.

3D Pose Estimation 6D Pose Estimation

6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference

2 code implementations ECCV 2020 Mai Bui, Tolga Birdal, Haowen Deng, Shadi Albarqouni, Leonidas Guibas, Slobodan Ilic, Nassir Navab

We present a multimodal camera relocalization framework that captures ambiguities and uncertainties with continuous mixture models defined on the manifold of camera poses.

Camera Relocalization

3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings

no code implementations8 Oct 2020 Giorgia Pitteri, Aurélie Bugeau, Slobodan Ilic, Vincent Lepetit

We demonstrate the performance of this approach on the T-LESS dataset, by using a small number of objects to learn the embedding and testing it on the other objects.

3D Object Detection object-detection +1

Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation

1 code implementation20 Dec 2020 Haowen Deng, Mai Bui, Nassir Navab, Leonidas Guibas, Slobodan Ilic, Tolga Birdal

For the former we contributed our own dataset composed of five indoor scenes where it is unavoidable to capture images corresponding to views that are hard to uniquely identify.

Camera Relocalization Pose Estimation

DistillPose: Lightweight Camera Localization Using Auxiliary Learning

no code implementations9 Aug 2021 Yehya Abouelnaga, Mai Bui, Slobodan Ilic

A siamese convolutional neural network regresses the relative pose from the nearest neighboring database image to the query image.

Auxiliary Learning Camera Localization +3

OSOP: A Multi-Stage One Shot Object Pose Estimation Framework

no code implementations CVPR 2022 Ivan Shugurov, Fu Li, Benjamin Busam, Slobodan Ilic

We present a novel one-shot method for object detection and 6 DoF pose estimation, that does not require training on target objects.

Object object-detection +2

Multi-View Object Pose Refinement With Differentiable Renderer

no code implementations6 Jul 2022 Ivan Shugurov, Ivan Pavlov, Sergey Zakharov, Slobodan Ilic

This paper introduces a novel multi-view 6 DoF object pose refinement approach focusing on improving methods trained on synthetic data.

Camera Calibration Object

DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation

no code implementations6 Jul 2022 Ivan Shugurov, Sergey Zakharov, Slobodan Ilic

The main conclusions is that RGB excels in correspondence estimation, while depth contributes to the pose accuracy if good 3D-3D correspondences are available.

Object object-detection +2

RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration

1 code implementation27 Sep 2022 Hao Yu, Ji Hou, Zheng Qin, Mahdi Saleh, Ivan Shugurov, Kai Wang, Benjamin Busam, Slobodan Ilic

More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions.

Point Cloud Registration

What can we learn about a generated image corrupting its latent representation?

no code implementations12 Oct 2022 Agnieszka Tomczak, Aarushi Gupta, Slobodan Ilic, Nassir Navab, Shadi Albarqouni

The purpose of this work is to investigate the hypothesis that we can predict image quality based on its latent representation in the GANs bottleneck.

Image-to-Image Translation Liver Segmentation

Rotation-Invariant Transformer for Point Cloud Matching

1 code implementation CVPR 2023 Hao Yu, Zheng Qin, Ji Hou, Mahdi Saleh, Dongsheng Li, Benjamin Busam, Slobodan Ilic

To this end, we introduce RoITr, a Rotation-Invariant Transformer to cope with the pose variations in the point cloud matching task.

Data Augmentation

MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images

no code implementations3 Mar 2024 Junwen Huang, Hao Yu, Kuan-Ting Yu, Nassir Navab, Slobodan Ilic, Benjamin Busam

MatchU is a generic approach that fuses 2D texture and 3D geometric cues for 6D pose prediction of unseen objects.

6D Pose Estimation Pose Prediction

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