相关论文: Automatic dataset generation for specific object d…

Deep vision models are now mature enough to be integrated in industrial and possibly critical applications such as autonomous navigation. Yet, data collection and labeling to train such models requires too much efforts and costs for a…

A major impediment in rapidly deploying object detection models for instance detection is the lack of large annotated datasets. For example, finding a large labeled dataset containing instances in a particular kitchen is unlikely. Each new…

Object detection is a fundamental task in computer vision, requiring large annotated datasets that are difficult to collect, as annotators need to label objects and their bounding boxes. Thus, it is a significant challenge to use cheaper…

In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…

Motivated by product detection in supermarkets, this paper studies the problem of object proposal generation in supermarket images and other natural images. We argue that estimation of object scales in images is helpful for generating…

Data seems cheap to get, and in many ways it is, but the process of creating a high quality labeled dataset from a mass of data is time-consuming and expensive. With the advent of rich 3D repositories, photo-realistic rendering systems…

Learning-based methods for 3D scene reconstruction and object completion require large datasets containing partial scans paired with complete ground-truth geometry. However, acquiring such datasets using real-world scanning systems is…

This work proposes a process for efficiently training a point-wise object detector that enables localizing objects and computing their 6D poses in cluttered and occluded scenes. Accurate pose estimation is typically a requirement for robust…

We introduce a novel robotic system for improving unseen object instance segmentation in the real world by leveraging long-term robot interaction with objects. Previous approaches either grasp or push an object and then obtain the…

The need for large annotated image datasets for training Convolutional Neural Networks (CNNs) has been a significant impediment for their adoption in computer vision applications. We show that with transfer learning an effective object…

Accurately controlling object count in text-to-image generation remains a key challenge. Supervised methods often fail, as training data rarely covers all count variations. Methods that manipulate the denoising process to add or remove…

This paper explores object detection in the small data regime, where only a limited number of annotated bounding boxes are available due to data rarity and annotation expense. This is a common challenge today with machine learning being…

An important factor in advancing autonomous driving systems is simulation. Yet, there is rather small progress for transferability between the virtual and real world. We revisit this problem for 3D object detection on LiDAR point clouds and…

Object detection is a crucial task in computer vision that aims to identify and localize objects in images or videos. The recent advancements in deep learning and Convolutional Neural Networks (CNNs) have significantly improved the…

Identifying objects in an image and their mutual relationships as a scene graph leads to a deep understanding of image content. Despite the recent advancement in deep learning, the detection and labeling of visual object relationships…

Text segmentation tasks have a very wide range of application values, such as image editing, style transfer, watermark removal, etc.However, existing public datasets are of poor quality of pixel-level labels that have been shown to be…

Object detection is an algorithm that recognizes and locates the objects in the image and has a wide range of applications in the visual understanding of complex urban scenes. Existing object detection benchmarks mainly focus on a single…

This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally,…

Aerial object detection is a challenging task, in which one major obstacle lies in the limitations of large-scale data collection and the long-tail distribution of certain classes. Synthetic data offers a promising solution, especially with…

In this paper, we propose a novel object-level mapping system that can simultaneously segment, track, and reconstruct objects in dynamic scenes. It can further predict and complete their full geometries by conditioning on reconstructions…