Search Results for author: Didier Stricker

Found 127 papers, 25 papers with code

Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer

no code implementations11 Jul 2024 Tahira Shehzadi, Ifza, Didier Stricker, Muhammad Zeshan Afzal

The impressive advancements in semi-supervised learning have driven researchers to explore its potential in object detection tasks within the field of computer vision.

Data Augmentation Object +3

CLEO: Continual Learning of Evolving Ontologies

no code implementations11 Jul 2024 Shishir Muralidhara, Saqib Bukhari, Georg Schneider, Didier Stricker, René Schuster

CLEO is a promising new approach to CL that addresses the challenge of evolving ontologies in real-world applications.

Autonomous Driving Continual Learning +1

EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Support

no code implementations3 Jul 2024 Ramy Battrawy, René Schuster, Didier Stricker

In this paper, we propose our EgoFlowNet - a point-level scene flow estimation network trained in a weakly-supervised manner and without object-based abstraction.

Clustering Object +1

RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds

no code implementations1 Jul 2024 Ramy Battrawy, René Schuster, Didier Stricker

Exhibiting high accuracy, our RMS-FlowNet++ provides a faster prediction than state-of-the-art methods, avoids high memory requirements and enables efficient scene flow on dense point clouds of more than 250K points at once.

Scene Flow Estimation

Shape2.5D: A Dataset of Texture-less Surfaces for Depth and Normals Estimation

1 code implementation22 Jun 2024 Muhammad Saif Ullah Khan, Muhammad Zeshan Afzal, Didier Stricker

Reconstructing texture-less surfaces poses unique challenges in computer vision, primarily due to the lack of specialized datasets that cater to the nuanced needs of depth and normals estimation in the absence of textural information.

Decoder Object Reconstruction

Situational Instructions Database: Task Guidance in Dynamic Environments

1 code implementation19 Jun 2024 Muhammad Saif Ullah Khan, Sankalp Sinha, Didier Stricker, Muhammad Zeshan Afzal

The Situational Instructions Database (SID) addresses the need for enhanced situational awareness in artificial intelligence (AI) systems operating in dynamic environments.

Decision Making

UnSupDLA: Towards Unsupervised Document Layout Analysis

no code implementations10 Jun 2024 Talha Uddin Sheikh, Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal

Moreover, the diversity of documents online presents a unique set of challenges in maintaining the quality and consistency of these labels, further complicating document layout analysis in the digital era.

Diversity Document Layout Analysis +2

End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documents

no code implementations8 May 2024 Iqraa Ehsan, Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal

Table detection, a pivotal task in document analysis, aims to precisely recognize and locate tables within document images.

Table Detection

CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification

no code implementations6 May 2024 Sankalp Sinha, Muhammad Saif Ullah Khan, Talha Uddin Sheikh, Didier Stricker, Muhammad Zeshan Afzal

We provide a comprehensive document image classification analysis in Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) settings to address this gap.

Document Classification Document Image Classification +1

Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer

no code implementations30 Apr 2024 Tahira Shehzadi, Shalini Sarode, Didier Stricker, Muhammad Zeshan Afzal

However, recent advancements in the field have shifted the focus towards transformer-based techniques, eliminating the need for NMS and emphasizing object queries and attention mechanisms.

Object Table Detection

A Hybrid Approach for Document Layout Analysis in Document images

no code implementations27 Apr 2024 Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal

This paper navigates the complexities of understanding various elements within document images, such as text, images, tables, and headings.

Contrastive Learning Decoder +5

Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection

no code implementations CVPR 2024 Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal

In this paper, we address the limitations of the DETR-based semi-supervised object detection (SSOD) framework, particularly focusing on the challenges posed by the quality of object queries.

Object object-detection +4

SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks

1 code implementation CVPR 2024 Yaxu Xie, Alain Pagani, Didier Stricker

The alignment between 3D scene graphs is the first step of many downstream tasks such as scene graph aided point cloud registration, mosaicking, overlap checking, and robot navigation.

3D Scene Graph Alignment Graph Matching +3

FocusCLIP: Multimodal Subject-Level Guidance for Zero-Shot Transfer in Human-Centric Tasks

no code implementations11 Mar 2024 Muhammad Saif Ullah Khan, Muhammad Ferjad Naeem, Federico Tombari, Luc van Gool, Didier Stricker, Muhammad Zeshan Afzal

We propose FocusCLIP, integrating subject-level guidance--a specialized mechanism for target-specific supervision--into the CLIP framework for improved zero-shot transfer on human-centric tasks.

Activity Recognition Age Classification +1

ShapeAug: Occlusion Augmentation for Event Camera Data

no code implementations4 Jan 2024 Katharina Bendig, René Schuster, Didier Stricker

This leads to a need for event data augmentation techniques in order to improve accuracy as well as to avoid over-fitting on the training data.

Data Augmentation Object +2

Learned Fusion: 3D Object Detection using Calibration-Free Transformer Feature Fusion

no code implementations14 Dec 2023 Michael Fürst, Rahul Jakkamsetty, René Schuster, Didier Stricker

The state of the art in 3D object detection using sensor fusion heavily relies on calibration quality, which is difficult to maintain in large scale deployment outside a lab environment.

3D Object Detection Object +2

ShapeGraFormer: GraFormer-Based Network for Hand-Object Reconstruction from a Single Depth Map

no code implementations18 Oct 2023 Ahmed Tawfik Aboukhadra, Jameel Malik, Nadia Robertini, Ahmed Elhayek, Didier Stricker

In addition, we show the impact of adding another GraFormer component that refines the reconstructed shapes based on the hand-object interactions and its ability to reconstruct more accurate object shapes.

3D Reconstruction Object +2

Cross-Dataset Experimental Study of Radar-Camera Fusion in Bird's-Eye View

no code implementations27 Sep 2023 Lukas Stäcker, Philipp Heidenreich, Jason Rambach, Didier Stricker

By exploiting complementary sensor information, radar and camera fusion systems have the potential to provide a highly robust and reliable perception system for advanced driver assistance systems and automated driving functions.

object-detection Object Detection +1

Introducing Language Guidance in Prompt-based Continual Learning

1 code implementation ICCV 2023 Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc van Gool, Didier Stricker, Federico Tombari, Muhammad Zeshan Afzal

While the model faces a disjoint set of classes in each task in this setting, we argue that these classes can be encoded to the same embedding space of a pre-trained language encoder.

Continual Learning

DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transport

no code implementations14 Aug 2023 Sk Aziz Ali, Djamila Aouada, Gerd Reis, Didier Stricker

In this work, we propose (i) partial optimal transportation of LiDAR feature descriptor for robust LO estimation, (ii) joint learning of predictive uncertainty while learning odometry over driving sequences, and (iii) demonstrate how PU can serve as evidence for necessary pose-graph optimization when LO network is either under or over confident.

Motion Planning Robot Navigation

U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds

1 code implementation ICCV 2023 Yan Di, Chenyangguang Zhang, Ruida Zhang, Fabian Manhardt, Yongzhi Su, Jason Rambach, Didier Stricker, Xiangyang Ji, Federico Tombari

In this paper, we propose U-RED, an Unsupervised shape REtrieval and Deformation pipeline that takes an arbitrary object observation as input, typically captured by RGB images or scans, and jointly retrieves and deforms the geometrically similar CAD models from a pre-established database to tightly match the target.

3D Shape Retrieval Retrieval

Light-Weight Vision Transformer with Parallel Local and Global Self-Attention

no code implementations18 Jul 2023 Nikolas Ebert, Laurenz Reichardt, Didier Stricker, Oliver Wasenmüller

In our work, we redesign the powerful state-of-the-art Vision Transformer PLG-ViT to a much more compact and efficient architecture that is suitable for such tasks.

Autonomous Driving Instance Segmentation +1

Achieving RGB-D level Segmentation Performance from a Single ToF Camera

no code implementations30 Jun 2023 Pranav Sharma, Jigyasa Singh Katrolia, Jason Rambach, Bruno Mirbach, Didier Stricker, Juergen Seiler

Depth is a very important modality in computer vision, typically used as complementary information to RGB, provided by RGB-D cameras.

Multi-Task Learning Segmentation +1

Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images

no code implementations23 Jun 2023 Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Zeshan Afzal

Upon integrating query modifications in the DETR, we outperform prior works and achieve new state-of-the-art results with the mAP of 96. 9\%, 95. 7\% and 99. 3\% on TableBank, PubLaynet, PubTables, respectively.

Document Layout Analysis Object +2

Object Detection with Transformers: A Review

2 code implementations7 Jun 2023 Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal

The astounding performance of transformers in natural language processing (NLP) has motivated researchers to explore their applications in computer vision tasks.

Object object-detection +1

RC-BEVFusion: A Plug-In Module for Radar-Camera Bird's Eye View Feature Fusion

no code implementations25 May 2023 Lukas Stäcker, Shashank Mishra, Philipp Heidenreich, Jason Rambach, Didier Stricker

Radars and cameras belong to the most frequently used sensors for advanced driver assistance systems and automated driving research.

3D Object Detection object-detection

Multi-task Fusion for Efficient Panoptic-Part Segmentation

no code implementations15 Dec 2022 Sravan Kumar Jagadeesh, René Schuster, Didier Stricker

For CPP, the PartPQ of our proposed model with joint fusion surpasses the previous state-of-the-art by 1. 6 and 4. 7 percentage points for all areas and segments with parts, respectively.

Image Segmentation Part-aware Panoptic Segmentation +2

Object Permanence in Object Detection Leveraging Temporal Priors at Inference Time

no code implementations28 Nov 2022 Michael Fürst, Priyash Bhugra, René Schuster, Didier Stricker

Humans understand this concept at young ages and know that another person is still there, even though it is temporarily occluded.

Object object-detection +1

OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection

no code implementations2 Nov 2022 Yongzhi Su, Yan Di, Fabian Manhardt, Guangyao Zhai, Jason Rambach, Benjamin Busam, Didier Stricker, Federico Tombari

Despite monocular 3D object detection having recently made a significant leap forward thanks to the use of pre-trained depth estimators for pseudo-LiDAR recovery, such two-stage methods typically suffer from overfitting and are incapable of explicitly encapsulating the geometric relation between depth and object bounding box.

Monocular 3D Object Detection Object +1

THOR-Net: End-to-end Graformer-based Realistic Two Hands and Object Reconstruction with Self-supervision

1 code implementation25 Oct 2022 Ahmed Tawfik Aboukhadra, Jameel Malik, Ahmed Elhayek, Nadia Robertini, Didier Stricker

In the features extraction stage, a Keypoint RCNN is used to extract 2D poses, features maps, heatmaps, and bounding boxes from a monocular RGB image.

Hand Pose Estimation Object Reconstruction

Learning Attention Propagation for Compositional Zero-Shot Learning

no code implementations20 Oct 2022 Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc van Gool, Alain Pagani, Didier Stricker, Muhammad Zeshan Afzal

CAPE learns to identify this structure and propagates knowledge between them to learn class embedding for all seen and unseen compositions.

Compositional Zero-Shot Learning

Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation

1 code implementation13 Oct 2022 Dipam Goswami, René Schuster, Joost Van de Weijer, Didier Stricker

In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift.

Overlapped 100-10 Overlapped 100-5 +7

Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection

no code implementations5 Oct 2022 Khurram Azeem Hashmi, Didier Stricker, Muhammamd Zeshan Afzal

Second, motivated by sequence-level semantic aggregation, we incorporate the attention-guided Semantic Proposal Feature Aggregation module to enhance object feature representation before detection.

Object object-detection +1

INV-Flow2PoseNet: Light-Resistant Rigid Object Pose from Optical Flow of RGB-D Images using Images, Normals and Vertices

no code implementations14 Sep 2022 Torben Fetzer, Gerd Reis, Didier Stricker

Based on the learned optical flows, a second architecture is proposed that predicts robust rigid transformations from the warped vertex and normal maps.

3D Reconstruction Optical Flow Estimation

Structure PLP-SLAM: Efficient Sparse Mapping and Localization using Point, Line and Plane for Monocular, RGB-D and Stereo Cameras

1 code implementation13 Jul 2022 Fangwen Shu, Jiaxuan Wang, Alain Pagani, Didier Stricker

One of the biggest challenges in parallel tracking and mapping with a monocular camera is to keep the scale consistent when reconstructing the geometric primitives.

Camera Localization Pose Tracking

Self-SuperFlow: Self-supervised Scene Flow Prediction in Stereo Sequences

no code implementations30 Jun 2022 Katharina Bendig, René Schuster, Didier Stricker

In recent years, deep neural networks showed their exceeding capabilities in addressing many computer vision tasks including scene flow prediction.

Learning Effect of Lay People in Gesture-Based Locomotion in Virtual Reality

no code implementations16 Jun 2022 Alexander Schäfer, Gerd Reis, Didier Stricker

In this work, it is investigated whether and how quickly users can adapt to a hand gesture-based locomotion system in VR.

Scale Invariant Semantic Segmentation with RGB-D Fusion

no code implementations10 Apr 2022 Mohammad Dawud Ansari, Alwi Husada, Didier Stricker

We propose to incorporate depth information to the RGB data for pixel-wise semantic segmentation to address the different scale objects in an outdoor scene.

Semantic Segmentation

Autoencoder for Synthetic to Real Generalization: From Simple to More Complex Scenes

1 code implementation1 Apr 2022 Steve Dias Da Cruz, Bertram Taetz, Thomas Stifter, Didier Stricker

Learning on synthetic data and transferring the resulting properties to their real counterparts is an important challenge for reducing costs and increasing safety in machine learning.

Autoencoder Attractors for Uncertainty Estimation

1 code implementation1 Apr 2022 Steve Dias Da Cruz, Bertram Taetz, Thomas Stifter, Didier Stricker

While input images close to known samples will converge to the same or similar attractor, input samples containing unknown features are unstable and converge to different training samples by potentially removing or changing characteristic features.

Gaussian Processes

RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds

no code implementations1 Apr 2022 Ramy Battrawy, René Schuster, Mohammad-Ali Nikouei Mahani, Didier Stricker

The proposed RMS-FlowNet is a novel end-to-end learning-based architecture for accurate and efficient scene flow estimation which can operate on point clouds of high density.

Scene Flow Estimation

Comparing Controller With the Hand Gestures Pinch and Grab for Picking Up and Placing Virtual Objects

no code implementations22 Feb 2022 Alexander Schäfer, Gerd Reis, Didier Stricker

Grabbing virtual objects is one of the essential tasks for Augmented, Virtual, and Mixed Reality applications.

Mixed Reality

SOMSI: Spherical Novel View Synthesis With Soft Occlusion Multi-Sphere Images

no code implementations CVPR 2022 Tewodros Habtegebrial, Christiano Gava, Marcel Rogge, Didier Stricker, Varun Jampani

We propose a novel MSI representation called Soft Occlusion MSI (SOMSI) that enables modelling high-dimensional appearance features in MSI while retaining the fast rendering times of a standard MSI.

Novel View Synthesis

Multi-scale Iterative Residuals for Fast and Scalable Stereo Matching

no code implementations25 Oct 2021 Kumail Raza, René Schuster, Didier Stricker

This paper presents an iterative multi-scale coarse-to-fine refinement (iCFR) framework to bridge this gap by allowing it to adopt any stereo matching network to make it fast, more efficient and scalable while keeping comparable accuracy.

Stereo Matching

Visual SLAM with Graph-Cut Optimized Multi-Plane Reconstruction

1 code implementation9 Aug 2021 Fangwen Shu, Yaxu Xie, Jason Rambach, Alain Pagani, Didier Stricker

This paper presents a semantic planar SLAM system that improves pose estimation and mapping using cues from an instance planar segmentation network.

Homography Estimation Pose Estimation

MutualEyeContact: A conversation analysis tool with focus on eye contact

no code implementations9 Jul 2021 Alexander Schäfer, Tomoko Isomura, Gerd Reis, Katsumi Watanabe, Didier Stricker

To further investigate the importance of eye contact in social interactions, portable eye tracking technology seems to be a natural choice.

Face Recognition

HandVoxNet++: 3D Hand Shape and Pose Estimation using Voxel-Based Neural Networks

no code implementations2 Jul 2021 Jameel Malik, Soshi Shimada, Ahmed Elhayek, Sk Aziz Ali, Christian Theobalt, Vladislav Golyanik, Didier Stricker

To address the limitations of the existing methods, we develop HandVoxNet++, i. e., a voxel-based deep network with 3D and graph convolutions trained in a fully supervised manner.

3D Hand Pose Estimation

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network Using Barnes-Hut 2D-Tree Representation

no code implementations CVPR 2021 Sk Aziz Ali, Kerem Kahraman, Gerd Reis, Didier Stricker

For this task, we use a novel 2^D-tree representation for the input point sets and a hierarchical deep feature embedding in the neural network.

Calibration and Auto-Refinement for Light Field Cameras

no code implementations11 Jun 2021 Yuriy Anisimov, Gerd Reis, Didier Stricker

The ability to create an accurate three-dimensional reconstruction of a captured scene draws attention to the principles of light fields.

Camera Calibration

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut $2^D$-Tree Representation

no code implementations12 Apr 2021 Sk Aziz Ali, Kerem Kahraman, Gerd Reis, Didier Stricker

For this task, we use a novel $2^D$-tree representation for the input point sets and a hierarchical deep feature embedding in the neural network.

TICaM: A Time-of-flight In-car Cabin Monitoring Dataset

no code implementations22 Mar 2021 Jigyasa Singh Katrolia, Bruno Mirbach, Ahmed El-Sherif, Hartmut Feld, Jason Rambach, Didier Stricker

We present TICaM, a Time-of-flight In-car Cabin Monitoring dataset for vehicle interior monitoring using a single wide-angle depth camera.

3D Object Detection Domain Adaptation +2

A Survey on Synchronous Augmented, Virtual and Mixed Reality Remote Collaboration Systems

no code implementations11 Feb 2021 Alexander Schäfer, Gerd Reis, Didier Stricker

Remote collaboration systems have become increasingly important in today's society, especially during times where physical distancing is advised.

Mixed Reality

Illumination Normalization by Partially Impossible Encoder-Decoder Cost Function

no code implementations6 Nov 2020 Steve Dias Da Cruz, Bertram Taetz, Thomas Stifter, Didier Stricker

Our method exploits the availability of identical sceneries under different illumination and environmental conditions for which we formulate a partially impossible reconstruction target: the input image will not convey enough information to reconstruct the target in its entirety.

Decoder

SLAM in the Field: An Evaluation of Monocular Mapping and Localization on Challenging Dynamic Agricultural Environment

no code implementations2 Nov 2020 Fangwen Shu, Paul Lesur, Yaxu Xie, Alain Pagani, Didier Stricker

This paper demonstrates a system capable of combining a sparse, indirect, monocular visual SLAM, with both offline and real-time Multi-View Stereo (MVS) reconstruction algorithms.

Autonomous Vehicles Depth Estimation

MonoComb: A Sparse-to-Dense Combination Approach for Monocular Scene Flow

no code implementations21 Oct 2020 René Schuster, Christian Unger, Didier Stricker

Contrary to the ongoing trend in automotive applications towards usage of more diverse and more sensors, this work tries to solve the complex scene flow problem under a monocular camera setup, i. e. using a single sensor.

Depth Estimation Optical Flow Estimation

HPERL: 3D Human Pose Estimation from RGB and LiDAR

1 code implementation16 Oct 2020 Michael Fürst, Shriya T. P. Gupta, René Schuster, Oliver Wasenmüller, Didier Stricker

In-the-wild human pose estimation has a huge potential for various fields, ranging from animation and action recognition to intention recognition and prediction for autonomous driving.

3D Human Pose Estimation Action Recognition +2

Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations

no code implementations28 Sep 2020 Sk Aziz Ali, Kerem Kahraman, Christian Theobalt, Didier Stricker, Vladislav Golyanik

This article introduces a new physics-based method for rigid point set alignment called Fast Gravitational Approach (FGA).

A survey on applications of augmented, mixed and virtual reality for nature and environment

no code implementations27 Aug 2020 Jason Rambach, Gergana Lilligreen, Alexander Schäfer, Ramya Bankanal, Alexander Wiebel, Didier Stricker

Augmented reality (AR), virtual reality (VR) and mixed reality (MR) are technologies of great potential due to the engaging and enriching experiences they are capable of providing.

Mixed Reality

SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation

no code implementations21 Aug 2020 René Schuster, Oliver Wasenmüller, Christian Unger, Didier Stricker

Interpolation of sparse pixel information towards a dense target resolution finds its application across multiple disciplines in computer vision.

Depth Completion Optical Flow Estimation

Generative View Synthesis: From Single-view Semantics to Novel-view Images

1 code implementation NeurIPS 2020 Tewodros Habtegebrial, Varun Jampani, Orazio Gallo, Didier Stricker

We propose to push the envelope further, and introduce Generative View Synthesis (GVS), which can synthesize multiple photorealistic views of a scene given a single semantic map.

Image Generation Translation

DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDAR

no code implementations18 Aug 2020 Rishav, Ramy Battrawy, René Schuster, Oliver Wasenmüller, Didier Stricker

In this paper, we present DeepLiDARFlow, a novel deep learning architecture which fuses high level RGB and LiDAR features at multiple scales in a monocular setup to predict dense scene flow.

3D Reconstruction Scene Flow Estimation

ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel Matching

no code implementations22 Jun 2020 Rishav, René Schuster, Ramy Battrawy, Oliver Wasenmüller, Didier Stricker

Thus, we present ResFPN -- a multi-resolution feature pyramid network with multiple residual skip connections, where at any scale, we leverage the information from higher resolution maps for stronger and better localized features.

Optical Flow Estimation Scene Flow Estimation

SVIRO: Synthetic Vehicle Interior Rear Seat Occupancy Dataset and Benchmark

1 code implementation10 Jan 2020 Steve Dias Da Cruz, Oliver Wasenmüller, Hans-Peter Beise, Thomas Stifter, Didier Stricker

We release SVIRO, a synthetic dataset for sceneries in the passenger compartment of ten different vehicles, in order to analyze machine learning-based approaches for their generalization capacities and reliability when trained on a limited number of variations (e. g. identical backgrounds and textures, few instances per class).

Instance Segmentation object-detection +3

LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Images

no code implementations31 Oct 2019 Ramy Battrawy, René Schuster, Oliver Wasenmüller, Qing Rao, Didier Stricker

We propose a new approach called LiDAR-Flow to robustly estimate a dense scene flow by fusing a sparse LiDAR with stereo images.

Scene Flow Estimation

Intrinsic Dynamic Shape Prior for Fast, Sequential and Dense Non-Rigid Structure from Motion with Detection of Temporally-Disjoint Rigidity

no code implementations5 Sep 2019 Vladislav Golyanik, André Jonas, Didier Stricker, Christian Theobalt

The reasons for the slow dissemination are the severe ill-posedness, high sensitivity to motion and deformation cues and the difficulty to obtain reliable point tracks in the vast majority of practical scenarios.

A Compact Light Field Camera for Real-Time Depth Estimation

no code implementations25 Jul 2019 Yuriy Anisimov, Oliver Wasenmüller, Didier Stricker

For the first time, we present a depth camera based on the light field principle, which provides real-time depth information as well as a compact design.

Depth Estimation

DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning Proxies

no code implementations24 Jul 2019 Soshi Shimada, Vladislav Golyanik, Edgar Tretschk, Didier Stricker, Christian Theobalt

We introduce a supervised-learning framework for non-rigid point set alignment of a new kind - Displacements on Voxels Networks (DispVoxNets) - which abstracts away from the point set representation and regresses 3D displacement fields on regularly sampled proxy 3D voxel grids.

Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data

no code implementations12 May 2019 Onorina Kovalenko, Vladislav Golyanik, Jameel Malik, Ahmed Elhayek, Didier Stricker

SfAM is highly robust to noisy 2D annotations, generalizes to arbitrary objects and does not rely on training data, which is shown in extensive experiments on public benchmarks and real video sequences.

3D Reconstruction

DeLiO: Decoupled LiDAR Odometry

no code implementations29 Apr 2019 Queens Maria Thomas, Oliver Wasenmüller, Didier Stricker

Most LiDAR odometry algorithms estimate the transformation between two consecutive frames by estimating the rotation and translation in an intervening fashion.

Translation

IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction

no code implementations27 Apr 2019 Soshi Shimada, Vladislav Golyanik, Christian Theobalt, Didier Stricker

The majority of the existing methods for non-rigid 3D surface regression from monocular 2D images require an object template or point tracks over multiple frames as an input, and are still far from real-time processing rates.

3D Reconstruction Generative Adversarial Network

PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation

1 code implementation12 Apr 2019 Rohan Saxena, René Schuster, Oliver Wasenmüller, Didier Stricker

In the last few years, convolutional neural networks (CNNs) have demonstrated increasing success at learning many computer vision tasks including dense estimation problems such as optical flow and stereo matching.

Optical Flow Estimation Scene Flow Estimation +2

An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching

no code implementations12 Apr 2019 René Schuster, Oliver Wasenmüller, Christian Unger, Didier Stricker

Not only the tuning of hyperparameters, but also the gathering and selection of training data, the design of the loss function, and the construction of training schedules is important to get the most out of a model.

Surface Defect Classification in Real-Time Using Convolutional Neural Networks

no code implementations7 Apr 2019 Selim Arikan, Kiran varanasi, Didier Stricker

Surface inspection systems are an important application domain for computer vision, as they are used for defect detection and classification in the manufacturing industry.

Classification Data Augmentation +2

Learning Quadrangulated Patches For 3D Shape Processing

no code implementations25 Mar 2019 Kripasindhu Sarkar, Kiran varanasi, Didier Stricker

We propose a system for surface completion and inpainting of 3D shapes using generative models, learnt on local patches.

Denoising

Structured 2D Representation of 3D Data for Shape Processing

no code implementations25 Mar 2019 Kripasindhu Sarkar, Elizabeth Mathews, Didier Stricker

We represent 3D shape by structured 2D representations of fixed length making it feasible to apply well investigated 2D convolutional neural networks (CNN) for both discriminative and geometric tasks on 3D shapes.

Classification General Classification

DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth

no code implementations28 Aug 2018 Jameel Malik, Ahmed Elhayek, Fabrizio Nunnari, Kiran varanasi, Kiarash Tamaddon, Alexis Heloir, Didier Stricker

Also, by employing a joint training strategy with real and synthetic data, we recover 3D hand mesh and pose from real images in 3. 7ms.

FlowFields++: Accurate Optical Flow Correspondences Meet Robust Interpolation

no code implementations9 May 2018 René Schuster, Christian Bailer, Oliver Wasenmüller, Didier Stricker

Thus, we propose in this paper FlowFields++, where we combine the accurate matches of Flow Fields with a robust interpolation.

Optical Flow Estimation

Fast Feature Extraction with CNNs with Pooling Layers

1 code implementation8 May 2018 Christian Bailer, Tewodros Habtegebrial, Kiran varanasi, Didier Stricker

In recent years, many publications showed that convolutional neural network based features can have a superior performance to engineered features.

Camera Calibration object-detection +3

Fast and Efficient Depth Map Estimation from Light Fields

no code implementations1 May 2018 Yuriy Anisimov, Didier Stricker

The paper presents an algorithm for depth map estimation from the light field images in relatively small amount of time, using only single thread on CPU.

Density Estimation

HDM-Net: Monocular Non-Rigid 3D Reconstruction with Learned Deformation Model

no code implementations27 Mar 2018 Vladislav Golyanik, Soshi Shimada, Kiran varanasi, Didier Stricker

Monocular dense 3D reconstruction of deformable objects is a hard ill-posed problem in computer vision.

3D Reconstruction

SceneFlowFields: Dense Interpolation of Sparse Scene Flow Correspondences

no code implementations27 Oct 2017 René Schuster, Oliver Wasenmüller, Georg Kuschk, Christian Bailer, Didier Stricker

While most scene flow methods use either variational optimization or a strong rigid motion assumption, we show for the first time that scene flow can also be estimated by dense interpolation of sparse matches.

Scalable Dense Monocular Surface Reconstruction

no code implementations17 Oct 2017 Mohammad Dawud Ansari, Vladislav Golyanik, Didier Stricker

This paper reports on a novel template-free monocular non-rigid surface reconstruction approach.

Surface Reconstruction

Multiframe Scene Flow with Piecewise Rigid Motion

no code implementations5 Oct 2017 Vladislav Golyanik, Kihwan Kim, Robert Maier, Matthias Nießner, Didier Stricker, Jan Kautz

We introduce a novel multiframe scene flow approach that jointly optimizes the consistency of the patch appearances and their local rigid motions from RGB-D image sequences.

Scene Flow Estimation

Learning quadrangulated patches for 3D shape parameterization and completion

no code implementations20 Sep 2017 Kripasindhu Sarkar, Kiran varanasi, Didier Stricker

By encoding 3D surface detail on local patches, we learn a patch dictionary that identifies principal surface features of the shape.

Denoising Dictionary Learning

Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation

no code implementations ICCV 2015 Christian Bailer, Bertram Taetz, Didier Stricker

In this article we present a dense correspondence field approach that is much less outlier-prone and thus much better suited for optical flow estimation than approximate nearest neighbor fields.

Optical Flow Estimation Patch Matching

Gravitational Approach for Point Set Registration

no code implementations CVPR 2016 Vladislav Golyanik, Sk Aziz Ali, Didier Stricker

In this paper a new astrodynamics inspired rigid point set registration algorithm is introduced -- the Gravitational Approach (GA).

Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation

no code implementations ICCV 2015 Christian Bailer, Bertram Taetz, Didier Stricker

In this paper we present a dense correspondence field approach that is much less outlier prone and thus much better suited for optical flow estimation than approximate nearest neighbor fields.

Optical Flow Estimation

Introducing a new benchmarked dataset for activity monitoring

no code implementations International Symposium on Wearable Computers 2012 Attila Reiss, Didier Stricker

This paper addresses the lack of a commonly used, standard dataset and established benchmarking problems for physical activity monitoring.

Benchmarking Classification

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