Related papers: AmodalSVG: Amodal Image Vectorization via Semantic…
The integration of language instructions with robotic control, particularly through Vision Language Action (VLA) models, has shown significant potential. However, these systems are often hindered by high computational costs, the need for…
We integrate smoothing B-splines into a standard differentiable vector graphics (DiffVG) pipeline through linear mapping, and show how this can be used to generate smooth and arbitrarily long paths within image-based deep learning systems.…
The success of VLMs often relies on the dynamic high-resolution schema that adaptively augments the input images to multiple crops, so that the details of the images can be retained. However, such approaches result in a large number of…
3D vision-language (VL) reasoning has gained significant attention due to its potential to bridge the 3D physical world with natural language descriptions. Existing approaches typically follow task-specific, highly specialized paradigms.…
Semantic image editing utilizes local semantic label maps to generate the desired content in the edited region. A recent work borrows SPADE block to achieve semantic image editing. However, it cannot produce pleasing results due to style…
Scalable Vector Graphics (SVG) is a popular format on the web and in the design industry. However, despite the great strides made in generative modeling, SVG has remained underexplored due to the discrete and complex nature of such data. We…
3D Visual Grounding (3DVG) focuses on locating objects in 3D scenes based on natural language descriptions, serving as a fundamental task for embodied AI and robotics. Recent advances in Multi-modal Large Language Models (MLLMs) have…
Converting raster floorplans into engineering-grade vector graphics is challenging due to complex topology and strict geometric constraints. To address this, we present FloorplanVLM, a unified framework that reformulates floorplan…
Visual Grounding (VG) aims to locate the most relevant region in an image, based on a flexible natural language query but not a pre-defined label, thus it can be a more useful technique than object detection in practice. Most…
Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answering by integrating visual and textual inputs. However, their robustness against adversarial…
Morphological methods play a crucial role in remote sensing image processing, due to their ability to capture and preserve small structural details. However, most of the existing deep learning models for semantic segmentation are based on…
Image modality is not perfect as it often fails in certain conditions, e.g., night and fast motion. This significantly limits the robustness and versatility of existing multi-modal (i.e., Image+X) semantic segmentation methods when…
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…
The goal of Audio-Visual Segmentation (AVS) is to localize and segment the sounding source objects from video frames. Research on AVS suffers from data scarcity due to the high cost of fine-grained manual annotations. Recent works attempt…
The rapid advancement of generative models has intensified the challenge of detecting and interpreting visual forgeries, necessitating robust frameworks for image forgery detection while providing reasoning as well as localization. While…
Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…
Recent years have witnessed substantial progress in semantic image synthesis, it is still challenging in synthesizing photo-realistic images with rich details. Most previous methods focus on exploiting the given semantic map, which just…
Scene graph generation provides a compact structured representation for visual perception, but accurate and fast graph prediction from images and videos remains challenging. Recent VLM-based methods can generate scene graphs end-to-end as…
Scene graphs offer a structured, hierarchical representation of images, with nodes and edges symbolizing objects and the relationships among them. It can serve as a natural interface for image editing, dramatically improving precision and…
Structure-guided image completion aims to inpaint a local region of an image according to an input guidance map from users. While such a task enables many practical applications for interactive editing, existing methods often struggle to…