Related papers: Towards Training-free Open-world Segmentation via …
Universal medical image segmentation seeks to use a single foundational model to handle diverse tasks across multiple imaging modalities. However, existing approaches often rely heavily on manual visual prompts or retrieved reference…
Nucleus instance segmentation in histology images is crucial for a broad spectrum of clinical applications. Current dominant algorithms rely on regression of nuclear proxy maps. Distinguishing nucleus instances from the estimated maps…
In recent years, notable advancements have been made in the domain of visual document understanding, with the prevailing architecture comprising a cascade of vision and language models. The text component can either be extracted explicitly…
Large-scale pretrained vision backbones have transformed computer vision by providing powerful feature extractors that enable various downstream tasks, including training-free approaches like visual prompting for semantic segmentation.…
Pixel-wise segmentation of laparoscopic scenes is essential for computer-assisted surgery but difficult to scale due to the high cost of dense annotations. We propose depth-guided surgical scene segmentation (DepSeg), a training-free…
Semantic segmentation is a crucial task in computer vision that involves segmenting images into semantically meaningful regions at the pixel level. However, existing approaches often rely on expensive human annotations as supervision for…
Large Vision-Language Models (VLMs) are increasingly being regarded as foundation models that can be instructed to solve diverse tasks by prompting, without task-specific training. We examine the seemingly obvious question: how to…
Cryo-electron microscopy (cryo-EM) remains pivotal in structural biology, yet the task of protein particle picking, integral for 3D protein structure construction, is laden with manual inefficiencies. While recent AI tools such as Topaz and…
Foundation models have taken over natural language processing and image generation domains due to the flexibility of prompting. With the recent introduction of the Segment Anything Model (SAM), this prompt-driven paradigm has entered image…
Recently, groundbreaking results have been presented on open-vocabulary semantic image segmentation. Such methods segment each pixel in an image into arbitrary categories provided at run-time in the form of text prompts, as opposed to a…
Remote sensing imagery has attracted significant attention in recent years due to its instrumental role in global environmental monitoring, land usage monitoring, and more. As image databases grow each year, performing automatic…
In this paper, we present PRISM, a Promptable and Robust Interactive Segmentation Model, aiming for precise segmentation of 3D medical images. PRISM accepts various visual inputs, including points, boxes, and scribbles as sparse prompts, as…
Nuclear instance segmentation and classification provide critical quantitative foundations for digital pathology diagnosis. With the advent of the foundational Segment Anything Model (SAM), the accuracy and efficiency of nuclear…
Accurate nuclear instance segmentation is a pivotal task in computational pathology, supporting data-driven clinical insights and facilitating downstream translational applications. While large vision foundation models have shown promise…
The Segment-Anything Model (SAM) is a vision foundation model for segmentation with a prompt-driven framework. SAM generates class-agnostic masks based on user-specified instance-referring prompts. However, adapting SAM for automated…
Segmenting 3D objects into parts is a long-standing challenge in computer vision. To overcome taxonomy constraints and generalize to unseen 3D objects, recent works turn to open-world part segmentation. These approaches typically transfer…
Segmentation in dense visual scenes poses significant challenges due to occlusions, background clutter, and scale variations. To address this, we introduce PerSense, an end-to-end, training-free, and model-agnostic one-shot framework for…
Text-to-Image Diffusion models excel at generating images from text prompts but often exhibit suboptimal alignment with content semantics, aesthetics, and human preferences. To address these limitations, this study proposes a novel…
Recent advancements in multimodal vision models have highlighted limitations in late-stage feature fusion and suboptimal query selection for hybrid prompts open-world segmentation, alongside constraints from caption-derived vocabularies. To…
Promptable foundation models such as the Segment Anything Model (SAM) produce high-quality masks but remain semantically blind, relying on external prompts to specify categories. Existing vision-language approaches address this limitation…