Related papers: PartSLIP++: Enhancing Low-Shot 3D Part Segmentatio…

As we push the boundaries of performance in various vision tasks, the models grow in size correspondingly. To keep up with this growth, we need very aggressive pruning techniques for efficient inference and deployment on edge devices.…

Independently exploring unknown spaces or finding objects in an indoor environment is a daily but challenging task for visually impaired people. However, common 2D assistive systems lack depth relationships between various objects,…

Partial-view 3D recognition -- reconstructing 3D geometry and identifying object instances from a few sparse RGB images -- is an exceptionally challenging yet practically essential task, particularly in cluttered, occluded real-world…

Pre-training across 3D vision and language remains under development because of limited training data. Recent works attempt to transfer vision-language pre-training models to 3D vision. PointCLIP converts point cloud data to multi-view…

Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors. Existing top-down approaches tackle this problem by either…

The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and…

In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…

Recent advances in foundational Vision Language Models (VLMs) have reshaped the evaluation paradigm in computer vision tasks. These foundational models, especially CLIP, have accelerated research in open-vocabulary computer vision tasks,…

Vision-Language models like CLIP have been widely adopted for various tasks due to their impressive zero-shot capabilities. However, CLIP is not suitable for extracting 3D geometric features as it was trained on only images and text by…

A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-resolution images. However, this approach introduces a new…

Remembering where object segments were predicted in the past is useful for improving the accuracy and consistency of class-agnostic video segmentation algorithms. Existing video segmentation algorithms typically use either no object-level…

Recent efforts to use natural language for interpretable driving focus mainly on planning, neglecting perception tasks. In this paper, we address this gap by introducing ROLISP (Risk Object Localization and Intention and Suggestion…

The Segment Anything Model (SAM) and CLIP are remarkable vision foundation models (VFMs). SAM, a prompt driven segmentation model, excels in segmentation tasks across diverse domains, while CLIP is renowned for its zero shot recognition…

Detecting objects in 3D LiDAR data is a core technology for autonomous driving and other robotics applications. Although LiDAR data is acquired over time, most of the 3D object detection algorithms propose object bounding boxes…

Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further…

Vision-Language Pre-training (VLP) models like CLIP have significantly advanced Remote Sensing Image-Text Retrieval (RSITR). However, existing methods predominantly rely on coarse-grained global alignment, which often overlooks the dense,…

Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. However, many of these works lack effective exploration of prior knowledge, rendering them…

Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set, which limits their application in real-world scenarios due to the lack of generalization ability. Large-scale visual-language…

As interest grows in world models that predict future states from current observations and actions, accurately modeling part-level dynamics has become increasingly relevant for various applications. Existing approaches, such as…

The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction. It has an extremely low training complexity while achieving state-of-the-art classification performance. In…