Related papers: V$^{2}$-SAM: Marrying SAM2 with Multi-Prompt Exper…

Subject-Driven Text-to-Image (T2I) Generation aims to preserve a subject's identity while editing its context based on a text prompt. A core challenge in this task is the "similarity-controllability paradox", where enhancing textual control…

Multimodal Large Language Models (MLLMs) have demonstrated strong image-level visual understanding and reasoning, yet their pixel-level perception across both images and videos remains limited. Foundation segmentation models such as the SAM…

Exemplar-based semantic image synthesis generates images aligned with semantic content while preserving the appearance of an exemplar. Conventional structure-guidance models like ControlNet, are limited as they rely solely on text prompts…

In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X employs the same Transformer-based encoder-decoder…

Object-goal navigation in open-vocabulary settings requires agents to locate novel objects in unseen environments, yet existing approaches suffer from opaque decision-making processes and low success rate on locating unseen objects. To…

One of the primary challenges in Synthetic Aperture Radar (SAR) object detection lies in the pervasive influence of coherent noise. As a common practice, most existing methods, whether handcrafted approaches or deep learning-based methods,…

Semantic correspondence (SC) aims to establish semantically meaningful matches across different instances of an object category. We illustrate how recent supervised SC methods remain limited in their ability to generalize beyond sparsely…

Accurate tongue segmentation is crucial for reliable TCM analysis. Supervised models require large annotated datasets, while SAM-family models remain prompt-driven. We present Memory-SAM, a training-free, human-prompt-free pipeline that…

To break through the limitations of pre-training models on fixed categories, Open-Set Object Detection (OSOD) and Open-Set Segmentation (OSS) have attracted a surge of interest from researchers. Inspired by large language models, mainstream…

Cross-view correspondence is a fundamental capability for spatial understanding and embodied AI. However, it is still far from being realized in Vision-Language Models (VLMs), especially in achieving precise point-level correspondence,…

World models allow agents to simulate the consequences of actions in imagined environments for planning, control, and long-horizon decision-making. However, existing autoregressive world models struggle with visually coherent predictions…

Language-Guided object recognition in remote sensing imagery is crucial for large-scale mapping and automated data annotation. However, existing open-vocabulary and visual grounding methods rely on explicit category cues, limiting their…

Cross-view object geo-localization (CVOGL) aims to determine the location of a specific object in high-resolution satellite imagery given a query image with a point prompt. Existing approaches treat CVOGL as a one-shot detection task,…

Large Vision--Language Models (LVLMs) hold great promise for advancing optical remote sensing (RS) analysis, yet existing reasoning segmentation frameworks couple linguistic reasoning and pixel prediction through end-to-end supervised…

The Segment Anything Model (SAM) is a deep neural network foundational model designed to perform instance segmentation which has gained significant popularity given its zero-shot segmentation ability. SAM operates by generating masks based…

Weakly-Supervised Concealed Object Segmentation (WSCOS) aims to segment objects well blended with surrounding environments using sparsely-annotated data for model training. It remains a challenging task since (1) it is hard to distinguish…

As the successor to the Segment Anything Model (SAM), the Segment Anything Model 2 (SAM2) not only improves performance in image segmentation but also extends its capabilities to video segmentation. However, its effectiveness in segmenting…

The Segment Anything Model 2 (SAM2) has demonstrated remarkable promptable visual segmentation capabilities in video data, showing potential for extension to medical image segmentation (MIS) tasks involving 3D volumes and temporally…

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…

The recently introduced Segment Anything Model (SAM), a Visual Foundation Model (VFM), has demonstrated impressive capabilities in zero-shot segmentation tasks across diverse natural image datasets. Despite its success, SAM encounters…