Related papers: Hardness-Aware Scene Synthesis for Semi-Supervised…

Point cloud segmentation with scene-level annotations is a promising but challenging task. Currently, the most popular way is to employ the class activation map (CAM) to locate discriminative regions and then generate point-level pseudo…

Synthetic data has been a critical tool for training scene text detection and recognition models. On the one hand, synthetic word images have proven to be a successful substitute for real images in training scene text recognizers. On the…

Object recognition and object pose estimation in robotic grasping continue to be significant challenges, since building a labelled dataset can be time consuming and financially costly in terms of data collection and annotation. In this…

Semi-supervised object detection (SSOD), leveraging unlabeled data to boost object detectors, has become a hot topic recently. However, existing SSOD approaches mainly focus on horizontal objects, leaving oriented objects common in aerial…

A crucial task in scene understanding is 3D object detection, which aims to detect and localize the 3D bounding boxes of objects belonging to specific classes. Existing 3D object detectors heavily rely on annotated 3D bounding boxes during…

3D Referring Expression Segmentation (3D-RES) typically requires extensive instance-level annotations, which are time-consuming and costly. Semi-supervised learning (SSL) mitigates this by using limited labeled data alongside abundant…

Learning 3D scene flow from LiDAR point clouds presents significant difficulties, including poor generalization from synthetic datasets to real scenes, scarcity of real-world 3D labels, and poor performance on real sparse LiDAR point…

Human-centric 3D scene understanding has recently drawn increasing attention, driven by its critical impact on robotics. However, human-centric real-life scenarios are extremely diverse and complicated, and humans have intricate motions and…

Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level…

Current LiDAR-based 3D object detectors for autonomous driving are almost entirely trained on human-annotated data collected in specific geographical domains with specific sensor setups, making it difficult to adapt to a different domain.…

3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation.…

Semi-supervised Learning (SSL) has received increasing attention in autonomous driving to reduce the enormous burden of 3D annotation. In this paper, we propose UpCycling, a novel SSL framework for 3D object detection with zero additional…

Current 3D object detection methods heavily rely on an enormous amount of annotations. Semi-supervised learning can be used to alleviate this issue. Previous semi-supervised 3D object detection methods directly follow the practice of…

The need for large amounts of training and validation data is a huge concern in scaling AI algorithms for autonomous driving. Semantic Image Synthesis (SIS), or label-to-image translation, promises to address this issue by translating…

Due to the high cost of annotating accurate pixel-level labels, semi-supervised learning has emerged as a promising approach for cloud detection. In this paper, we propose CloudMatch, a semi-supervised framework that effectively leverages…

Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such…

Deep learning-based video salient object detection has recently achieved great success with its performance significantly outperforming any other unsupervised methods. However, existing data-driven approaches heavily rely on a large…

Dynamic scene reconstruction is a long-term challenge in 3D vision. Existing plane-based methods in dynamic Gaussian splatting suffer from an unsuitable low-rank assumption, causing feature overlap and poor rendering quality. Although 4D…

3D object detection is essential for understanding 3D scenes. Contemporary techniques often require extensive annotated training data, yet obtaining point-wise annotations for point clouds is time-consuming and laborious. Recent…

Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However, it is both time-consuming and challenging to obtain consistently accurate annotations for such 3D scene data. Moreover, there is…