Search Results for author:
Found 94 papers, 16 papers with code
RC-BEVFusion: A Plug-In Module for Radar-Camera Bird's Eye View Feature Fusion
Radars and cameras belong to the most frequently used sensors for advanced driver assistance systems and automated driving research.
Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer
Table detection is the task of classifying and localizing table objects within document images.
Multi-task Fusion for Efficient Panoptic-Part Segmentation
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.
I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification
Our proposed model, I2MVFormer, learns multi-view semantic embeddings for zero-shot image classification with these class views.
Object Permanence in Object Detection Leveraging Temporal Priors at Inference Time
Humans understand this concept at young ages and know that another person is still there, even though it is temporarily occluded.
OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection
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.
THOR-Net: End-to-end Graformer-based Realistic Two Hands and Object Reconstruction with Self-supervision
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.
Learning Attention Propagation for Compositional Zero-Shot Learning
CAPE learns to identify this structure and propagates knowledge between them to learn class embedding for all seen and unseen compositions.
Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation
In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift.
Ranked #1 on
Overlapped 14-1
on Cityscapes
BoxMask: Revisiting Bounding Box Supervision for Video Object Detection
We present a new, simple yet effective approach to uplift video object detection.
Ranked #8 on
Video Object Detection
on ImageNet VID
Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection
Second, motivated by sequence-level semantic aggregation, we incorporate the attention-guided Semantic Proposal Feature Aggregation module to enhance object feature representation before detection.
Ranked #19 on
Video Object Detection
on ImageNet VID
INV-Flow2PoseNet: Light-Resistant Rigid Object Pose from Optical Flow of RGB-D Images using Images, Normals and Vertices
Based on the learned optical flows, a second architecture is proposed that predicts robust rigid transformations from the warped vertex and normal maps.
Structure PLP-SLAM: Efficient Sparse Mapping and Localization using Point, Line and Plane for Monocular, RGB-D and Stereo Cameras
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.
The Gesture Authoring Space: Authoring Customised Hand Gestures for Grasping Virtual Objects in Immersive Virtual Environments
In a user study, the proposed approach is compared with the pinch gesture and the controller for grasping virtual objects.
Self-SuperFlow: Self-supervised Scene Flow Prediction in Stereo Sequences
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
In this work, it is investigated whether and how quickly users can adapt to a hand gesture-based locomotion system in VR.
SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion
Depth completion involves recovering a dense depth map from a sparse map and an RGB image.
Ranked #1 on
Depth Completion
on KITTI Depth Completion
Scale Invariant Semantic Segmentation with RGB-D Fusion
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.
Autoencoder for Synthetic to Real Generalization: From Simple to More Complex Scenes
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.
RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds
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.
Autoencoder Attractors for Uncertainty Estimation
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.
ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation
Dense methods also improved pose estimation in the presence of occlusion.
Unsupervised Anomaly Detection from Time-of-Flight Depth Images
Video anomaly detection (VAD) addresses the problem of automatically finding anomalous events in video data.
Comparing Controller With the Hand Gestures Pinch and Grab for Picking Up and Placing Virtual Objects
Grabbing virtual objects is one of the essential tasks for Augmented, Virtual, and Mixed Reality applications.
SOMSI: Spherical Novel View Synthesis With Soft Occlusion Multi-Sphere Images
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.
IKEA Object State Dataset: A 6DoF object pose estimation dataset and benchmark for multi-state assembly objects
Utilizing 6DoF(Degrees of Freedom) pose information of an object and its components is critical for object state detection tasks.
Multi-scale Iterative Residuals for Fast and Scalable Stereo Matching
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.
PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB Image
Piece-wise 3D planar reconstruction provides holistic scene understanding of man-made environments, especially for indoor scenarios.
TIMo -- A Dataset for Indoor Building Monitoring with a Time-of-Flight Camera
Most existing surveillance video datasets provide either grayscale or RGB videos.
Deployment of Deep Neural Networks for Object Detection on Edge AI Devices with Runtime Optimization
We therefore perform a case study of the deployment of two representative object detection networks on an edge AI platform.
Visual SLAM with Graph-Cut Optimized Multi-Plane Reconstruction
This paper presents a semantic planar SLAM system that improves pose estimation and mapping using cues from an instance planar segmentation network.
MutualEyeContact: A conversation analysis tool with focus on eye contact
To further investigate the importance of eye contact in social interactions, portable eye tracking technology seems to be a natural choice.
HandVoxNet++: 3D Hand Shape and Pose Estimation using Voxel-Based Neural Networks
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.
RPSRNet: End-to-End Trainable Rigid Point Set Registration Network Using Barnes-Hut 2D-Tree Representation
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
The ability to create an accurate three-dimensional reconstruction of a captured scene draws attention to the principles of light fields.
Autoencoder Based Inter-Vehicle Generalization for In-Cabin Occupant Classification
Common domain shift problem formulations consider the integration of multiple source domains, or the target domain during training.
Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks
Table understanding has substantially benefited from the recent breakthroughs in deep neural networks.
Guided Table Structure Recognition through Anchor Optimization
Subsequently, these anchors are exploited to locate the rows and columns in tabular images.
RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut $2^D$-Tree Representation
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.
PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN
Our model employs a variant of a fast single-stage CNN architecture to segment plane instances.
TICaM: A Time-of-flight In-car Cabin Monitoring Dataset
We present TICaM, a Time-of-flight In-car Cabin Monitoring dataset for vehicle interior monitoring using a single wide-angle depth camera.
SALT: A Semi-automatic Labeling Tool for RGB-D Video Sequences
Large labeled data sets are one of the essential basics of modern deep learning techniques.
A Survey on Synchronous Augmented, Virtual and Mixed Reality Remote Collaboration Systems
Remote collaboration systems have become increasingly important in today's society, especially during times where physical distancing is advised.
Illumination Normalization by Partially Impossible Encoder-Decoder Cost Function
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.
A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions
Motion estimation is one of the core challenges in computer vision.
SLAM in the Field: An Evaluation of Monocular Mapping and Localization on Challenging Dynamic Agricultural Environment
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.
MonoComb: A Sparse-to-Dense Combination Approach for Monocular Scene Flow
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.
HPERL: 3D Human Pose Estimation from RGB and LiDAR
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.
Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations
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
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.
SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation
Interpolation of sparse pixel information towards a dense target resolution finds its application across multiple disciplines in computer vision.
Generative View Synthesis: From Single-view Semantics to Novel-view Images
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.
DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDAR
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.
ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel Matching
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.
LRPD: Long Range 3D Pedestrian Detection Leveraging Specific Strengths of LiDAR and RGB
The evaluation of our LRPD approach was done on the pedestrians from the KITTI benchmark.
Object Detection and Recognition of Swap-Bodies using Camera mounted on a Vehicle
Collecting enough images for training the model is a critical step towards achieving good results.
HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Map
The input to our method is a 3D voxelized depth map, and we rely on two hand shape representations.
DFKI Cabin Simulator: A Test Platform for Visual In-Cabin Monitoring Functions
We present a test platform for visual in-cabin scene analysis and occupant monitoring functions.
SVIRO: Synthetic Vehicle Interior Rear Seat Occupancy Dataset and Benchmark
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).
LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Images
We propose a new approach called LiDAR-Flow to robustly estimate a dense scene flow by fusing a sparse LiDAR with stereo images.
Intrinsic Dynamic Shape Prior for Fast, Sequential and Dense Non-Rigid Structure from Motion with Detection of Temporally-Disjoint Rigidity
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.
Rapid Light Field Depth Estimation with Semi-Global Matching
Running time of the light field depth estimation algorithms is typically high.
A Compact Light Field Camera for Real-Time Depth Estimation
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.
DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning Proxies
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
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.
DeLiO: Decoupled LiDAR Odometry
Most LiDAR odometry algorithms estimate the transformation between two consecutive frames by estimating the rotation and translation in an intervening fashion.
IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction
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.
PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation
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.
Ranked #1 on
Scene Flow Estimation
on KITTI 2015 Scene Flow Test
An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching
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
Surface inspection systems are an important application domain for computer vision, as they are used for defect detection and classification in the manufacturing industry.
SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks
Our network has a very large receptive field and avoids striding layers to maintain spatial resolution.
Learning Quadrangulated Patches For 3D Shape Processing
We propose a system for surface completion and inpainting of 3D shapes using generative models, learnt on local patches.
Structured 2D Representation of 3D Data for Shape Processing
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.
SceneFlowFields++: Multi-frame Matching, Visibility Prediction, and Robust Interpolation for Scene Flow Estimation
State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness.
Automated Scene Flow Data Generation for Training and Verification
Scene flow describes the 3D position as well as the 3D motion of each pixel in an image.
Dense Scene Flow from Stereo Disparity and Optical Flow
Scene flow describes 3D motion in a 3D scene.
DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth
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.
Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks
We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs.
FlowFields++: Accurate Optical Flow Correspondences Meet Robust Interpolation
Thus, we propose in this paper FlowFields++, where we combine the accurate matches of Flow Fields with a robust interpolation.
Fast Feature Extraction with CNNs with Pooling Layers
In recent years, many publications showed that convolutional neural network based features can have a superior performance to engineered features.
Fast and Efficient Depth Map Estimation from Light Fields
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.
Fast View Synthesis with Deep Stereo Vision
Novel view synthesis is an important problem in computer vision and graphics.
HDM-Net: Monocular Non-Rigid 3D Reconstruction with Learned Deformation Model
Monocular dense 3D reconstruction of deformable objects is a hard ill-posed problem in computer vision.
Combining Stereo Disparity and Optical Flow for Basic Scene Flow
Scene flow is a description of real world motion in 3D that contains more information than optical flow.
Accurate 3D Reconstruction of Dynamic Scenes from Monocular Image Sequences with Severe Occlusions
We integrate a shape prior term into variational optimisation framework.
Simultaneous Hand Pose and Skeleton Bone-Lengths Estimation from a Single Depth Image
Articulated hand pose estimation is a challenging task for human-computer interaction.
SceneFlowFields: Dense Interpolation of Sparse Scene Flow Correspondences
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
This paper reports on a novel template-free monocular non-rigid surface reconstruction approach.
Multiframe Scene Flow with Piecewise Rigid Motion
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.
Learning quadrangulated patches for 3D shape parameterization and completion
By encoding 3D surface detail on local patches, we learn a patch dictionary that identifies principal surface features of the shape.
Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation
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.
CNN-based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss
In this paper, we present a CNN based patch matching approach for optical flow estimation.
Gravitational Approach for Point Set Registration
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
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.
