Related papers: Breaking the Box: Enhancing Remote Sensing Image S…
Text-to-image models are showcasing the impressive ability to create high-quality and diverse generative images. Nevertheless, the transition from freehand sketches to complex scene images remains challenging using diffusion models. In this…
Interactive segmentation allows efficient label generation by leveraging user-provided clicks to progressively refine predictions, which is critical when fully supervised labels are costly or generalization to unseen classes is needed.…
Few-shot semantic segmentation aims to segment objects from previously unseen classes using only a limited number of labeled examples. In this paper, we introduce Label Anything, a novel transformer-based architecture designed for…
Sampling of signals belonging to a low-dimensional subspace has well-documented merits for dimensionality reduction, limited memory storage, and online processing of streaming network data. When the subspace is known, these signals can be…
Spatial-query-by-sketch is an intuitive tool to explore human spatial knowledge about geographic environments and to support communication with scene database queries. However, traditional sketch-based spatial search methods perform…
Sketches make an intuitive and powerful visual expression as they are fast executed freehand drawings. We present a method for synthesizing realistic photos from scene sketches. Without the need for sketch and photo pairs, our framework…
Sketching is a widely used medium for generating and exploring early-stage design concepts. While generative AI (GenAI) chatbots are increasingly used for idea generation, designers often struggle to craft effective prompts and find it…
We present RealitySketch, an augmented reality interface for sketching interactive graphics and visualizations. In recent years, an increasing number of AR sketching tools enable users to draw and embed sketches in the real world. However,…
The widespread adoption of autonomous systems such as drones and assistant robots has created a need for real-time high-quality semantic scene segmentation. In this paper, we propose an efficient yet robust technique for on-the-fly dense…
Accurate interpretation of street-level imagery is essential for large-scale urban mapping and the creation of Spatial Digital Twin (SDT) environments. This work presents a unified framework for joint 2D-3D segmentation and association that…
Graph streams represent data interactions in real applications. The mining of graph streams plays an important role in network security, social network analysis, and traffic control, among others. However, the sheer volume and high dynamics…
In this paper, we democratise 3D content creation, enabling precise generation of 3D shapes from abstract sketches while overcoming limitations tied to drawing skills. We introduce a novel part-level modelling and alignment framework that…
This work proposes a novel method for object co-segmentation, i.e. pixel-level localization of a common object in a set of images, that uses no pixel-level supervision for training. Two pre-trained Vision Transformer (ViT) models are…
Researchers have explored various ways to generate realistic images from freehand sketches, e.g., for objects and human faces. However, how to generate realistic human body images from sketches is still a challenging problem. It is, first…
Remote sensing scene classification has experienced a paradigmatic transformation from traditional handcrafted feature methods to sophisticated artificial intelligence systems that now form the backbone of modern Earth observation…
Semantic segmentation of remote sensing images is a fundamental task in geospatial research. However, widely used Convolutional Neural Networks (CNNs) and Transformers have notable drawbacks: CNNs may be limited by insufficient remote…
Despite the growing use of large language models (LLMs) for providing feedback, limited research has explored how to achieve high-quality feedback. This case study introduces an evaluation framework to assess different zero-shot prompt…
For more efficient generalization to unseen domains (classes), most Few-shot Segmentation (FSS) would directly exploit pre-trained encoders and only fine-tune the decoder, especially in the current era of large models. However, such fixed…
Understanding and reasoning about complex 3D environments requires structured scene representations that capture not only objects but also their semantic and spatial relationships. While recent works on 3D scene graph generation have…
Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated…