Search Results for author:
Found 85 papers, 41 papers with code
Tracking by 3D Model Estimation of Unknown Objects in Videos
We argue that this representation is limited and instead propose to guide and improve 2D tracking with an explicit object representation, namely the textured 3D shape and 6DoF pose in each video frame.
Calibrated Out-of-Distribution Detection with a Generic Representation
In this work, we take a different approach and propose to leverage generic pre-trained representations.
Video shutter angle estimation using optical flow and linear blur
The approach exploits the relation of the exposure fraction, optical flow, and linear motion blur.
BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objects
In 2022, we witnessed another significant improvement in the pose estimation accuracy -- the state of the art, which was 56. 9 AR$_C$ in 2019 (Vidal et al.) and 69. 8 AR$_C$ in 2020 (CosyPose), moved to new heights of 83. 7 AR$_C$ (GDRNPP).
A Large Scale Homography Benchmark
We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D.
Planar Object Tracking via Weighted Optical Flow
We propose WOFT -- a novel method for planar object tracking that estimates a full 8 degrees-of-freedom pose, i. e. the homography w. r. t.
A Large-Scale Homography Benchmark
We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D.
Generalized Differentiable RANSAC
We propose $\nabla$-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline.
Trans2k: Unlocking the Power of Deep Models for Transparent Object Tracking
Visual object tracking has focused predominantly on opaque objects, while transparent object tracking received very little attention.
HRF-Net: Holistic Radiance Fields from Sparse Inputs
We present HRF-Net, a novel view synthesis method based on holistic radiance fields that renders novel views using a set of sparse inputs.
Human keypoint detection for close proximity human-robot interaction
In particular, (i) we survey existing datasets with human pose annotation from the perspective of close proximity images and prepare and make publicly available a new Human in Close Proximity (HiCP) dataset; (ii) we quantitatively and qualitatively compare state-of-the-art human whole-body 2D keypoint detection methods (OpenPose, MMPose, AlphaPose, Detectron2) on this dataset; (iii) since accurate detection of hands and fingers is critical in applications with handovers, we evaluate the performance of the MediaPipe hand detector; (iv) we deploy the algorithms on a humanoid robot with an RGB-D camera on its head and evaluate the performance in 3D human keypoint detection.
Fast Neural Architecture Search for Lightweight Dense Prediction Networks
We present LDP, a lightweight dense prediction neural architecture search (NAS) framework.
Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook
Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems.
Deep MAGSAC++
We propose Deep MAGSAC++ combining the advantages of traditional and deep robust estimators.
Point Cloud Color Constancy
In this paper, we present Point Cloud Color Constancy, in short PCCC, an illumination chromaticity estimation algorithm exploiting a point cloud.
Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds
Humans can robustly recognize and localize objects by using visual and/or auditory cues.
Recall@k Surrogate Loss with Large Batches and Similarity Mixup
This work focuses on learning deep visual representation models for retrieval by exploring the interplay between a new loss function, the batch size, and a new regularization approach.
Ranked #1 on
Vehicle Re-Identification
on VehicleID Small
Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss
In addition, we introduce a normalized Hessian loss term invariant to scaling and shear along the depth direction, which is shown to substantially improve the accuracy.
Lightweight Monocular Depth with a Novel Neural Architecture Search Method
This paper presents a novel neural architecture search method, called LiDNAS, for generating lightweight monocular depth estimation models.
The Hitchhiker's Guide to Prior-Shift Adaptation
In many computer vision classification tasks, class priors at test time often differ from priors on the training set.
VSAC: Efficient and Accurate Estimator for H and F
Experiments on four standard datasets show that VSAC is significantly faster than all its predecessors and runs on average in 1-2 ms, on a CPU.
USACv20: robust essential, fundamental and homography matrix estimation
We review the most recent RANSAC-like hypothesize-and-verify robust estimators.
Finding Geometric Models by Clustering in the Consensus Space
Dominant instances are found via a RANSAC-like sampling and a consolidation process driven by a model quality function considering previously proposed instances.
FEDS -- Filtered Edit Distance Surrogate
This paper proposes a procedure to train a scene text recognition model using a robust learned surrogate of edit distance.
Road Anomaly Detection by Partial Image Reconstruction With Segmentation Coupling
To that end, we propose a reconstruction module that can be used with many existing semantic segmentation networks, and that is trained to recognize and reconstruct road (drivable) surface from a small bottleneck.
Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion
In this paper, we propose enhancing monocular depth estimation by adding 3D points as depth guidance.
FMODetect: Robust Detection of Fast Moving Objects
Compared to other methods, such as deblatting, the inference is of several orders of magnitude faster and allows applications such as real-time fast moving object detection and retrieval in large video collections.
DeFMO: Deblurring and Shape Recovery of Fast Moving Objects
We propose a method that, given a single image with its estimated background, outputs the object's appearance and position in a series of sub-frames as if captured by a high-speed camera (i. e. temporal super-resolution).
Ranked #1 on
Video Super-Resolution
on Falling Objects
RGBD-Net: Predicting color and depth images for novel views synthesis
We propose a new cascaded architecture for novel view synthesis, called RGBD-Net, which consists of two core components: a hierarchical depth regression network and a depth-aware generator network.
Efficient Initial Pose-graph Generation for Global SfM
We propose ways to speed up the initial pose-graph generation for global Structure-from-Motion algorithms.
Fast Fourier Intrinsic Network
We address the problem of decomposing an image into albedo and shading.
ArXiving Before Submission Helps Everyone
We claim, and present evidence, that allowing arXiv publication before a conference or journal submission benefits researchers, especially early career, as well as the whole scientific community.
BOP Challenge 2020 on 6D Object Localization
This paper presents the evaluation methodology, datasets, and results of the BOP Challenge 2020, the third in a series of public competitions organized with the goal to capture the status quo in the field of 6D object pose estimation from an RGB-D image.
Text Recognition -- Real World Data and Where to Find Them
We present a method for exploiting weakly annotated images to improve text extraction pipelines.
Learning Surrogates via Deep Embedding
The effectiveness of the proposed technique is demonstrated in a post-tuning setup, where a trained model is tuned using the learned surrogate.
Guiding Monocular Depth Estimation Using Depth-Attention Volume
Recovering the scene depth from a single image is an ill-posed problem that requires additional priors, often referred to as monocular depth cues, to disambiguate different 3D interpretations.
EPOS: Estimating 6D Pose of Objects with Symmetries
A data-dependent number of corresponding 3D locations is selected per pixel, and poses of possibly multiple object instances are estimated using a robust and efficient variant of the PnP-RANSAC algorithm.
A Benchmark for Temporal Color Constancy
The conventional approach is to use a single frame - shot frame - to estimate the scene illumination color.
Image Matching across Wide Baselines: From Paper to Practice
We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric.
MAGSAC++, a fast, reliable and accurate robust estimator
A new method for robust estimation, MAGSAC++, is proposed.
DAL -- A Deep Depth-aware Long-term Tracker
In this work, we propose a deep depth-aware long-term tracker that achieves state-of-the-art RGBD tracking performance and is fast to run.
Sub-frame Appearance and 6D Pose Estimation of Fast Moving Objects
We propose a novel method that tracks fast moving objects, mainly non-uniform spherical, in full 6 degrees of freedom, estimating simultaneously their 3D motion trajectory, 3D pose and object appearance changes with a time step that is a fraction of the video frame exposure time.
Ranked #1 on
Video Super-Resolution
on TbD
ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
With the growing cosmopolitan culture of modern cities, the need of robust Multi-Lingual scene Text (MLT) detection and recognition systems has never been more immense.
Cultural Vocal Bursts Intensity Prediction
General Classification
+1
Progressive-X: Efficient, Anytime, Multi-Model Fitting Algorithm
The Progressive-X algorithm, Prog-X in short, is proposed for geometric multi-model fitting.
Progressive NAPSAC: sampling from gradually growing neighborhoods
We propose Progressive NAPSAC, P-NAPSAC in short, which merges the advantages of local and global sampling by drawing samples from gradually growing neighborhoods.
Rolling Shutter Camera Synchronization with Sub-millisecond Accuracy
A simple method for synchronization of video streams with a precision better than one millisecond is proposed.
Flash Lightens Gray Pixels
In the real world, a scene is usually cast by multiple illuminants and herein we address the problem of spatial illumination estimation.
On Finding Gray Pixels
We propose a novel grayness index for finding gray pixels and demonstrate its effectiveness and efficiency in illumination estimation.
Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters
Standard RGB-D trackers treat the target as an inherently 2D structure, which makes modelling appearance changes related even to simple out-of-plane rotation highly challenging.
LSD$_2$ -- Joint Denoising and Deblurring of Short and Long Exposure Images with CNNs
The paper addresses the problem of acquiring high-quality photographs with handheld smartphone cameras in low-light imaging conditions.
A Summary of the 4th International Workshop on Recovering 6D Object Pose
The workshop featured four invited talks, oral and poster presentations of accepted workshop papers, and an introduction of the BOP benchmark for 6D object pose estimation.
Gyroscope-Aided Motion Deblurring with Deep Networks
We propose a deblurring method that incorporates gyroscope measurements into a convolutional neural network (CNN).
BOP: Benchmark for 6D Object Pose Estimation
We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input image.
Performance Analysis and Robustification of Single-query 6-DoF Camera Pose Estimation
We consider a single-query 6-DoF camera pose estimation with reference images and a point cloud, i. e. the problem of estimating the position and orientation of a camera by using reference images and a point cloud.
Fast Motion Deblurring for Feature Detection and Matching Using Inertial Measurements
It is well-known that motion blur decreases the performance of traditional feature detectors and descriptors.
Improving CNN classifiers by estimating test-time priors
The proposed Maximum a Posteriori estimation increases the prediction accuracy by 2. 8% on PlantCLEF 2017 and by 1. 8% on FGVCx Fungi, where the existing MLE method would lead to a decrease accuracy.
Detecting Decision Ambiguity from Facial Images
We propose a baseline method combining a deep convolutional neural network with an SVM.
Revisiting Gray Pixel for Statistical Illumination Estimation
We present a statistical color constancy method that relies on novel gray pixel detection and mean shift clustering.
MAGSAC: marginalizing sample consensus
A method called, sigma-consensus, is proposed to eliminate the need for a user-defined inlier-outlier threshold in RANSAC.
E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text
An end-to-end trainable (fully differentiable) method for multi-language scene text localization and recognition is proposed.
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
The quality of the deblurring model is also evaluated in a novel way on a real-world problem -- object detection on (de-)blurred images.
Ranked #3 on
Deblurring
on REDS
Repeatability Is Not Enough: Learning Affine Regions via Discriminability
A method for learning local affine-covariant regions is presented.
Ranked #4 on
Image Matching
on IMC PhotoTourism
(using extra training data)
Recurrent Color Constancy
We introduce a novel formulation of temporal color constancy which considers multiple frames preceding the frame for which illumination is estimated.
Deep TextSpotter: An End-To-End Trainable Scene Text Localization and Recognition Framework
A method for scene text localization and recognition is proposed.
Graph-Cut RANSAC
A novel method for robust estimation, called Graph-Cut RANSAC, GC-RANSAC in short, is introduced.
Multi-Class Model Fitting by Energy Minimization and Mode-Seeking
The move replaces a set of labels with the corresponding density mode in the model parameter domain, thus achieving fast and robust optimization.
Working hard to know your neighbor's margins: Local descriptor learning loss
We introduce a novel loss for learning local feature descriptors which is inspired by the Lowe's matching criterion for SIFT.
T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects
There are approximately 39K training and 10K test images from each sensor.
Inertial-Based Scale Estimation for Structure from Motion on Mobile Devices
In the process, we also perform a temporal and spatial alignment of the camera and the IMU.
The World of Fast Moving Objects
The notion of a Fast Moving Object (FMO), i. e. an object that moves over a distance exceeding its size within the exposure time, is introduced.
In the Saddle: Chasing Fast and Repeatable Features
A novel similarity-covariant feature detector that extracts points whose neighbourhoods, when treated as a 3D intensity surface, have a saddle-like intensity profile.
Deep Structured-Output Regression Learning for Computational Color Constancy
Computational color constancy that requires esti- mation of illuminant colors of images is a fundamental yet active problem in computer vision, which can be formulated into a regression problem.
Systematic evaluation of CNN advances on the ImageNet
The paper systematically studies the impact of a range of recent advances in CNN architectures and learning methods on the object categorization (ILSVRC) problem.
From Dusk Till Dawn: Modeling in the Dark
We present an algorithm that leverages the appearance variety to obtain more complete and accurate scene geometry along with consistent multi-illumination appearance information.
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
The goal of COCO-Text is to advance state-of-the-art in text detection and recognition in natural images.
FASText: Efficient Unconstrained Scene Text Detector
After a novel efficient classification step, the number of regions is reduced to 7 times less than the standard method and is still almost 3 times faster.
All you need is a good init
Experiment with different activation functions (maxout, ReLU-family, tanh) show that the proposed initialization leads to learning of very deep nets that (i) produces networks with test accuracy better or equal to standard methods and (ii) is at least as fast as the complex schemes proposed specifically for very deep nets such as FitNets (Romero et al. (2015)) and Highway (Srivastava et al. (2015)).
Ranked #23 on
Image Classification
on MNIST
Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object Detection
The efficiency is achieved by the use of spatial bins in a novel combination with sparsity-inducing group normalized SVM.
WxBS: Wide Baseline Stereo Generalizations
We have presented a new problem -- the wide multiple baseline stereo (WxBS) -- which considers matching of images that simultaneously differ in more than one image acquisition factor such as viewpoint, illumination, sensor type or where object appearance changes significantly, e. g. over time.
Online Adaptive Hidden Markov Model for Multi-Tracker Fusion
We show the effectiveness of the proposed method on combination of two and three tracking algorithms.
MODS: Fast and Robust Method for Two-View Matching
A novel algorithm for wide-baseline matching called MODS - Matching On Demand with view Synthesis - is presented.
A Novel Performance Evaluation Methodology for Single-Target Trackers
This paper addresses the problem of single-target tracker performance evaluation.
Detection, Rectification and Segmentation of Coplanar Repeated Patterns
This paper presents a novel and general method for the detection, rectification and segmentation of imaged coplanar repeated patterns.
Detection of Partially Visible Objects
An "elephant in the room" for most current object detection and localization methods is the lack of explicit modelling of partial visibility due to occlusion by other objects or truncation by the image boundary.
Two-View Matching with View Synthesis Revisited
Wide-baseline matching focussing on problems with extreme viewpoint change is considered.
