Abstract We introduce the Segment Anything (SA) project: a new task, model, and dataset for
image segmentation. Using our efficient model in a data collection loop, we built the largest …

The Segment Anything Model (SAM) has recently gained popularity in the field of image
segmentation due to its impressive capabilities in various segmentation tasks and its prompt …

In this work, we introduce Semantic-SAM, an augmented image segmentation foundation for
segmenting and recognizing anything at desired granularities. Compared to the …

Interactive segmentation is a crucial research area in medical image analysis aiming to
boost the efficiency of costly annotations by incorporating human feedback. This feedback …

Click-based interactive image segmentation aims at extracting objects with a limited user
clicking. A hierarchical backbone is the de-facto architecture for current methods. Recently …

Image segmentation is one of the most basic tasks in computer vision and remains an initial
step of many applications. In this paper, we focus on interactive image segmentation (IIS) …

Interactive segmentation allows users to extract target masks by making positive/negative
clicks. Although explored by many previous works, there is still a gap between academic …

We propose an end-to-end deep learning architecture that produces a 3D shape in
triangular mesh from a single color image. Limited by the nature of deep neural network …

Recent works on click-based interactive segmentation have demonstrated state-of-the-art
results by using various inference-time optimization schemes. These methods are …

Controllable image captioning is an emerging multimodal topic that aims to describe the
image with natural language following human purpose, $\textit {eg} $, looking at the …