相关论文: RRSIS: Referring Remote Sensing Image Segmentation

We present LlamaSeg, a visual autoregressive framework that unifies multiple image segmentation tasks via natural language instructions. We reformulate image segmentation as a visual generation problem, representing masks as "visual" tokens…

Medical image segmentation remains challenging due to intensity inhomogeneity, noise, blurred boundaries, and irregular structures. Traditional level set methods, while effective in certain cases, often depend on approximate bias field…

Salient object detection (SOD) for optical remote sensing images (RSIs) aims at locating and extracting visually distinctive objects/regions from the optical RSIs. Despite some saliency models were proposed to solve the intrinsic problem of…

Real-time semantic segmentation of remote sensing imagery is a challenging task that requires a trade-off between effectiveness and efficiency. It has many applications including tracking forest fires, detecting changes in land use and land…

Referring Medical Image Sequence Segmentation (Ref-MISS) is a novel and challenging task that aims to segment anatomical structures in medical image sequences (\emph{e.g.} endoscopy, ultrasound, CT, and MRI) based on natural language…

We investigate Referring Image Segmentation (RIS), which outputs a segmentation map corresponding to the natural language description. Addressing RIS efficiently requires considering the interactions happening across visual and linguistic…

3D Referring Expression Segmentation (3D-RES) aims to segment 3D objects by correlating referring expressions with point clouds. However, traditional approaches frequently encounter issues like over-segmentation or mis-segmentation, due to…

Referring image segmentation, the task of segmenting any arbitrary entities described in free-form texts, opens up a variety of vision applications. However, manual labeling of training data for this task is prohibitively costly, leading to…

This paper proposes a novel method for high-quality image segmentation of both objects and scenes. Inspired by the dilation and erosion operations in morphological image processing techniques, the pixel-level image segmentation problems are…

We present REM, a framework for segmenting a wide range of concepts in video that can be described through natural language. Our method leverages the universal visual-language mapping learned by video diffusion models on Internet-scale data…

In this paper, we present a high-performance and light-weight deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the aerial scene of a remote sensing image. To this end, we first valuate various…

Recent advancements in diffusion models (DMs) have greatly advanced remote sensing image super-resolution (RSISR). However, their iterative sampling processes often result in slow inference speeds, limiting their application in real-time…

Remote sensing has become critical for understanding environmental dynamics, urban planning, and disaster management. However, traditional remote sensing workflows often rely on explicit segmentation or detection methods, which struggle to…

The core objective of image captioning is to achieve lossless semantic compression from visual signals into textual modalities. However, the reliance on manually curated reference texts for evaluation essentially forces models to mimic…

In this work, we address the task of referring image segmentation (RIS), which aims at predicting a segmentation mask for the object described by a natural language expression. Most existing methods focus on establishing unidirectional or…

Semantic segmentation of Very High Resolution (VHR) remote sensing images is a fundamental task for many applications. However, large variations in the scales of objects in those VHR images pose a challenge for performing accurate semantic…

Remote sensing change understanding (RSCU) is essential for analyzing remote sensing images and understanding how human activities affect the environment. However, existing datasets lack deep understanding and interactions in the diverse…

Referring video object segmentation (RVOS) aims to segment objects in videos guided by natural language descriptions. We propose FS-RVOS, a Transformer-based model with two key components: a cross-modal affinity module and an instance…

Sparse annotation in remote sensing object detection poses significant challenges due to dense object distributions and category imbalances. Although existing Dense Pseudo-Label methods have demonstrated substantial potential in…

Referring 3D Segmentation is a visual-language task that segments all points of the specified object from a 3D point cloud described by a sentence of query. Previous works perform a two-stage paradigm, first conducting language-agnostic…