Related papers: INSID3: Training-Free In-Context Segmentation with…

Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of text-defined categories, demanding reliable generalization to unseen classes at inference. Although modern vision-language models (VLMs) support…

Given a single labeled example, in-context segmentation aims to segment corresponding objects. This setting, known as one-shot segmentation in few-shot learning, explores the segmentation model's generalization ability and has been applied…

The remote sensing (RS) domain suffers from a lack of densely labeled datasets, which are costly to obtain. Thus, models that can segment RS imagery well without supervised fine-tuning are valuable, but existing solutions fall behind…

In this paper, we present the One-shot In-context Part Segmentation (OIParts) framework, designed to tackle the challenges of part segmentation by leveraging visual foundation models (VFMs). Existing training-based one-shot part…

3D instance segmentation is fundamental to geometric understanding of the world around us. Existing methods for instance segmentation of 3D scenes rely on supervision from expensive, manual 3D annotations. We propose UnScene3D, the first…

While Contrastive Language-Image Pre-training (CLIP) has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatial-invariant semantic features and…

Building models that generalize across physical systems without retraining remains a central challenge in computational science. Here we introduce In-Context Modeling (ICM), a retrain-free paradigm that infers physical relationships…

Foundation models for interactive segmentation in 2D natural images and videos have sparked significant interest in building 3D foundation models for medical imaging. However, the domain gaps and clinical use cases for 3D medical imaging…

Benchmarking 3D spatial understanding of foundation models is essential for real-world applications such as robotics and autonomous driving. Existing evaluations often rely on downstream fine-tuning with linear heads or task-specific…

Accurate segmentation of organs and tumors in CT and MRI scans is essential for diagnosis, treatment planning, and disease monitoring. While deep learning has advanced automated segmentation, most models remain task-specific, lacking…

Instance segmentation enables the analysis of spatial and temporal properties of cells in microscopy images by identifying the pixels belonging to each cell. However, progress is constrained by the scarcity of high-quality labeled…

We propose MinVIS, a minimal video instance segmentation (VIS) framework that achieves state-of-the-art VIS performance with neither video-based architectures nor training procedures. By only training a query-based image instance…

While recent feed-forward 3D reconstruction models provide a strong geometric foundation for scene understanding, extending them to 3D instance segmentation typically relies on a disjointed "lift-and-cluster" paradigm. Grouping dense…

Open-Vocabulary Segmentation (OVS) aims at segmenting images from free-form textual concepts without predefined training classes. While existing vision-language models such as CLIP can generate segmentation masks by leveraging coarse…

Vision foundation models pretrained on web-scale data have recently shown strong transfer capabilities on many downstream tasks, but their effectiveness for industrial visual inspection remains unclear. Industrial data differ substantially…

Adnexal mass evaluation via ultrasound is a challenging clinical task, often hindered by subjective interpretation and significant inter-observer variability. While automated segmentation is a foundational step for quantitative risk…

Functionality segmentation in 3D scenes requires an agent to ground implicit natural-language instructions into precise masks of fine-grained interactive elements. Existing methods rely on fragmented pipelines that suffer from visual…

Training-free Camouflaged Object Segmentation (COS) seeks to segment camouflaged objects without task-specific training, by automatically generating visual prompts to guide the Segment Anything Model (SAM). However, existing pipelines…

Instance segmentation is essential for numerous computer vision applications, including robotics, human-computer interaction, and autonomous driving. Currently, popular models bring impressive performance in instance segmentation by…

Foundation models pre-trained on large-scale natural image datasets offer a powerful paradigm for medical image segmentation. However, effectively transferring their learned representations for precise clinical applications remains a…