Related papers: Identifying Systematic Errors in Object Detectors …

Object compositing based on 2D images is a challenging problem since it typically involves multiple processing stages such as color harmonization, geometry correction and shadow generation to generate realistic results. Furthermore,…

Deep neural network (DNN) architectures have been shown to outperform traditional pipelines for object segmentation and pose estimation using RGBD data, but the performance of these DNN pipelines is directly tied to how representative the…

Conventional video segmentation approaches rely heavily on appearance models. Such methods often use appearance descriptors that have limited discriminative power under complex scenarios. To improve the segmentation performance, this paper…

Data pipelines are an essential component for end-to-end solutions that take machine learning algorithms to production. Engineering data pipelines for video-sequences poses several challenges including isolation of key-frames from video…

Structure-guided image completion aims to inpaint a local region of an image according to an input guidance map from users. While such a task enables many practical applications for interactive editing, existing methods often struggle to…

Deep learning approaches to object detection have achieved reliable detection of specific object classes in images. However, extending a model's detection capability to new object classes requires large amounts of annotated training data,…

This paper presents a state-of-the-art approach in object detection for being applied in future SLAM problems. Although, many SLAM methods are proposed to create suitable autonomy for mobile robots namely ground vehicles, they still face…

Infrared imagery can help in low-visibility situations such as fog and low-light scenarios, but it is prone to thermal noise and requires further processing and correction. This work studies the effect of different infrared processing…

Small object detection is a broadly investigated research task and is commonly conceptualized as a "pipeline-style" engineering process. In the upstream, images serve as raw materials for processing in the detection pipeline, where…

Multi-object tracking (MOT) is a challenging practical problem for vision based applications. Most recent approaches for MOT use precomputed detections from models such as Faster RCNN, performing fine-tuning of bounding boxes and…

Dynamic Scene Graph Generation (DSGG) focuses on identifying visual relationships within the spatial-temporal domain of videos. Conventional approaches often employ multi-stage pipelines, which typically consist of object detection,…

The performance of neural network models is often limited by the availability of big data sets. To treat this problem, we survey and develop novel synthetic data generation and augmentation techniques for enhancing low/zero-sample learning…

In this paper, we present a new method for detecting road users in an urban environment which leads to an improvement in multiple object tracking. Our method takes as an input a foreground image and improves the object detection and…

Many creative ideas are being proposed for image sensor designs, and these may be useful in applications ranging from consumer photography to computer vision. To understand and evaluate each new design, we must create a corresponding image…

State-of-the-art detection systems are generally evaluated on their ability to exhaustively retrieve objects densely distributed in the image, across a wide variety of appearances and semantic categories. Orthogonal to this, many real-life…

This paper provides a novel approach to stitching surface images of rotationally symmetric parts. It presents a process pipeline that uses a feature-based stitching approach to create a distortion-free and true-to-life image from a video…

Recent development of 3D sensors allows the acquisition of extremely dense 3D point clouds of large-scale scenes. The main challenge of processing such large point clouds remains in the size of the data, which induce expensive computational…

Tremendous progress in deep learning over the last years has led towards a future with autonomous vehicles on our roads. Nevertheless, the performance of their perception systems is strongly dependent on the quality of the utilized training…

The bottleneck in learning-based industrial defect detection is often limited not by model capacity, but by the scarcity of labeled defect data: defects are rare, annotations are expensive, and collecting balanced training sets is slow. We…

Synthetic data is being used lately for training deep neural networks in computer vision applications such as object detection, object segmentation and 6D object pose estimation. Domain randomization hereby plays an important role in…