Related papers: Context-Aware Transformer for 3D Point Cloud Autom…

Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. However, existing methods for model adaptation usually update all model parameters, i.e., full fine-tuning paradigm, which is…

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer…

3D dense captioning is a task involving the localization of objects and the generation of descriptions for each object in a 3D scene. Recent approaches have attempted to incorporate contextual information by modeling relationships with…

Annotating object ground truth in videos is vital for several downstream tasks in robot perception and machine learning, such as for evaluating the performance of an object tracker or training an image-based object detector. The accuracy of…

Transformer models have achieved promising performances in point cloud segmentation. However, most existing attention schemes provide the same feature learning paradigm for all points equally and overlook the enormous difference in size…

Recently, LiDAR point cloud processing and analysis have made great progress due to the development of 3D Transformers. However, existing 3D Transformer methods usually are computationally expensive and inefficient due to their huge and…

Manual annotation of bounding boxes for object detection in digital images is tedious, and time and resource consuming. In this paper, we propose a semi-automatic method for efficient bounding box annotation. The method trains the object…

Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g., autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by…

In most modern object detection pipelines, the detection proposals are processed independently given the feature map. Therefore, they overlook the underlying relationships between objects and the surrounding background, which could have…

One-shot transfer of dexterous grasps to novel scenes with object and context variations has been a challenging problem. While distilled feature fields from large vision models have enabled semantic correspondences across 3D scenes, their…

As three-dimensional (3D) data acquisition devices become increasingly prevalent, the demand for 3D point cloud transmission is growing. In this study, we introduce a semantic-aware communication system for robust point cloud classification…

In the field of autonomous driving, there have been many excellent perception models for object detection, semantic segmentation, and other tasks, but how can we effectively use the perception models for vehicle planning? Traditional…

The recent success of neural networks enables a better interpretation of 3D point clouds, but processing a large-scale 3D scene remains a challenging problem. Most current approaches divide a large-scale scene into small regions and combine…

Change captioning has become essential for accurately describing changes in multi-temporal remote sensing data, providing an intuitive way to monitor Earth's dynamics through natural language. However, existing change captioning methods…

Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which…

We introduce Intelligent Annotation Dialogs for bounding box annotation. We train an agent to automatically choose a sequence of actions for a human annotator to produce a bounding box in a minimal amount of time. Specifically, we consider…

Given a query patch from a novel class, one-shot object detection aims to detect all instances of that class in a target image through the semantic similarity comparison. However, due to the extremely limited guidance in the novel class as…

Object detection using LiDAR point clouds relies on a large amount of human-annotated samples when training the underlying detectors' deep neural networks. However, generating 3D bounding box annotation for a large-scale dataset could be…

Achieving robust 3D perception in the face of corrupted data presents an challenging hurdle within 3D vision research. Contemporary transformer-based point cloud recognition models, albeit advanced, tend to overfit to specific patterns,…

In Autonomous Driving (AD), detection and tracking of obstacles on the roads is a critical task. Deep-learning based methods using annotated LiDAR data have been the most widely adopted approach for this. Unfortunately, annotating 3D point…