Related papers: PartSTAD: 2D-to-3D Part Segmentation Task Adaptati…

3D object detection in point cloud data remains a challenging task due to the sparsity and lack of global structure inherent in the input. In this work, we propose a novel Multi-Scale Attention (MSA) mechanism integrated into the 3DETR…

Localizing object parts precisely is essential for tasks such as object recognition and robotic manipulation. Recent part segmentation methods require extensive training data and labor-intensive annotations. Segment-Anything Model (SAM) has…

Structural accuracy of segmentation is important for finescale structures in biomedical images. We propose a novel TopologyAttention ConvLSTM Network (TACNet) for 3D image segmentation in order to achieve high structural accuracy for 3D…

Although point-based networks are demonstrated to be accurate for 3D point cloud modeling, they are still falling behind their voxel-based competitors in 3D detection. We observe that the prevailing set abstraction design for down-sampling…

Recent advances in medical image segmentation have been driven by deep learning; however, most existing methods remain limited by modality-specific designs and exhibit poor adaptability to dynamic medical imaging scenarios. The Segment…

3D point clouds are rich in geometric structure information, while 2D images contain important and continuous texture information. Combining 2D information to achieve better 3D semantic segmentation has become mainstream in 3D scene…

The open vocabulary capability of 3D models is increasingly valued, as traditional methods with models trained with fixed categories fail to recognize unseen objects in complex dynamic 3D scenes. In this paper, we propose a simple yet…

Parameter-efficient finetuning (PEFT) methods effectively adapt large language models (LLMs) to diverse downstream tasks, reducing storage and GPU memory demands. Despite these advantages, several applications pose new challenges to PEFT…

Ground segmentation is crucial for terrestrial mobile platforms to perform navigation or neighboring object recognition. Unfortunately, the ground is not flat, as it features steep slopes; bumpy roads; or objects, such as curbs, flower…

The popularity of pre-trained large models has revolutionized downstream tasks across diverse fields, such as language, vision, and multi-modality. To minimize the adaption cost for downstream tasks, many Parameter-Efficient Fine-Tuning…

Recently, foundation models trained on massive datasets to adapt to a wide range of tasks have attracted considerable attention and are actively being explored within the computer vision community. Among these, the Segment Anything Model…

The problem of segmenting a given image into coherent regions is important in Computer Vision and many industrial applications require segmenting a known object into its components. Examples include identifying individual parts of a…

The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and…

Recent methods for long-tailed instance segmentation still struggle on rare object classes with few training data. We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data…

State-of-the-art vessel segmentation methods typically require large-scale annotated datasets and suffer from severe performance degradation under domain shifts. In clinical practice, however, acquiring extensive annotations for every new…

In this paper, we introduce a method for adapting the step-sizes of temporal difference (TD) learning. The performance of TD methods often depends on well chosen step-sizes, yet few algorithms have been developed for setting the step-size…

Segment Anything Model (SAM), a new AI model from Meta AI released in April 2023, is an ambitious tool designed to identify and separate individual objects within a given image through semantic interpretation. The advanced capabilities of…

As capturing devices become common, 3D scans of interior spaces are acquired on a daily basis. Through scene comparison over time, information about objects in the scene and their changes is inferred. This information is important for…

Image segmentation and 3D pose estimation are two key cogs in any algorithm for scene understanding. However, state-of-the-art CRF-based models for image segmentation rely mostly on 2D object models to construct top-down high-order…

This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve generalization under domain shifts commonly encountered in real-world autonomous driving. A…