相关论文: Synthetic-to-Real Camouflaged Object Detection

Autonomous driving relies on a huge volume of real-world data to be labeled to high precision. Alternative solutions seek to exploit driving simulators that can generate large amounts of labeled data with a plethora of content variations.…

In the field of autonomous driving, sensor simulation is essential for generating rare and diverse scenarios that are difficult to capture in real-world environments. Current solutions fall into two categories: 1) CG-based methods, such as…

Current collaborative perception methods often rely on fully annotated datasets, which can be expensive to obtain in practical situations. To reduce annotation costs, some works adopt sparsely supervised learning techniques and generate…

We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the…

Accurate product information is critical for e-commerce stores to allow customers to browse, filter, and search for products. Product data quality is affected by missing or incorrect information resulting in poor customer experience. While…

Scene Parsing is a crucial step to enable autonomous systems to understand and interact with their surroundings. Supervised deep learning methods have made great progress in solving scene parsing problems, however, come at the cost of…

Unsupervised domain adaptation for LiDAR-based 3D object detection (3D UDA) based on the teacher-student architecture with pseudo labels has achieved notable improvements in recent years. Although it is quite popular to collect point clouds…

Spacecraft Pose Estimation (SPE) is a fundamental capability for autonomous space operations such as rendezvous, docking, and in-orbit servicing. Hybrid pipelines that combine object detection, keypoint regression, and Perspective-n-Point…

Acquiring labeled 6D poses from real images is an expensive and time-consuming task. Though massive amounts of synthetic RGB images are easy to obtain, the models trained on them suffer from noticeable performance degradation due to the…

Reconstructing low-dimensional truth labels from high-dimensional experimental data is a central challenge in any scenario that relies on robust mappings across this so-called domain gap, from multi-particle final states in high-energy…

Facial action unit (AU) detection is a fundamental block for objective facial expression analysis. Supervised learning approaches require a large amount of manual labeling which is costly. The limited labeled data are also not diverse in…

Person re-identification (Re-ID) is an important task and has significant applications for public security and information forensics, which has progressed rapidly with the development of deep learning. In this work, we investigate a novel…

Semi-supervised learning (SSL) can improve model performance by leveraging unlabeled images, which can be collected from public image sources with low costs. In recent years, synthetic images have become increasingly common in public image…

Concealed object detection (COD) in cluttered scenes is significant for various image processing applications. However, due to that concealed objects are always similar to their background, it is extremely hard to distinguish them. Here,…

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. In DETR-based SSOD, the one-to-one assignment…

We show a straightforward and useful methodology for performing instance segmentation using synthetic data. We apply this methodology on a basic case and derived insights through quantitative analysis. We created a new public dataset: The…

The ability to segment unknown objects in depth images has potential to enhance robot skills in grasping and object tracking. Recent computer vision research has demonstrated that Mask R-CNN can be trained to segment specific categories of…

Scene segmentation via unsupervised domain adaptation (UDA) enables the transfer of knowledge acquired from source synthetic data to real-world target data, which largely reduces the need for manual pixel-level annotations in the target…

Existing roadside perception systems are limited by the absence of publicly available, large-scale, high-quality 3D datasets. Exploring the use of cost-effective, extensive synthetic datasets offers a viable solution to tackle this…

In order to handle the challenges of autonomous driving, deep learning has proven to be crucial in tackling increasingly complex tasks, such as 3D detection or instance segmentation. State-of-the-art approaches for image-based detection…