This paper describes a multi-modal data association method for global localization using object-based maps and camera images. In global localization, or relocalization, using object-based maps, existing methods typically resort to matching all possible combinations of detected objects and landmarks with the same object category, followed by inlier extraction using RANSAC or brute-force search. This approach becomes infeasible as the number of landmarks increases due to the exponential growth of correspondence candidates. In this paper, we propose labeling landmarks with natural language descriptions and extracting correspondences based on conceptual similarity with image observations using a Vision Language Model (VLM). By leveraging detailed text information, our approach efficiently extracts correspondences compared to methods using only object categories. Through experiments, we demonstrate that the proposed method enables more accurate global localization with fewer iterations compared to baseline methods, exhibiting its efficiency.
Despite the recent advances in large-scale diffusion models, little progress has been made on the layout-to-image (L2I) synthesis task. Current L2I models either suffer from poor editability via text or weak alignment between the generated image and the input layout. This limits their usability in practice. To mitigate this, we propose to integrate adversarial supervision into the conventional training pipeline of L2I diffusion models (ALDM). Specifically, we employ a segmentation-based discriminator which provides explicit feedback to the diffusion generator on the pixel-level alignment between the denoised image and the input layout. To encourage consistent adherence to the input layout over the sampling steps, we further introduce the multistep unrolling strategy. Instead of looking at a single timestep, we unroll a few steps recursively to imitate the inference process, and ask the discriminator to assess the alignment of denoised images with the layout over a certain time window. Our experiments show that ALDM enables layout faithfulness of the generated images, while allowing broad editability via text prompts. Moreover, we showcase its usefulness for practical applications: by synthesizing target distribution samples via text control, we improve domain generalization of semantic segmentation models by a large margin (~12 mIoU points).
Visual foundation models have achieved remarkable results in zero-shot image classification and segmentation, but zero-shot change detection remains an open problem. In this paper, we propose the segment any change models (AnyChange), a new type of change detection model that supports zero-shot prediction and generalization on unseen change types and data distributions. AnyChange is built on the segment anything model (SAM) via our training-free adaptation method, bitemporal latent matching. By revealing and exploiting intra-image and inter-image semantic similarities in SAM's latent space, bitemporal latent matching endows SAM with zero-shot change detection capabilities in a training-free way. We also propose a point query mechanism to enable AnyChange's zero-shot object-centric change detection capability. We perform extensive experiments to confirm the effectiveness of AnyChange for zero-shot change detection. AnyChange sets a new record on the SECOND benchmark for unsupervised change detection, exceeding the previous SOTA by up to 4.4% F$_1$ score, and achieving comparable accuracy with negligible manual annotations (1 pixel per image) for supervised change detection.
With the continuous advancement of imaging devices, the prevalence of Ultra-High-Definition (UHD) images is rising. Although many image restoration methods have achieved promising results, they are not directly applicable to UHD images on devices with limited computational resources due to the inherently high computational complexity of UHD images. In this paper, we focus on the task of low-light image enhancement (LLIE) and propose a novel LLIE method called MixNet, which is designed explicitly for UHD images. To capture the long-range dependency of features without introducing excessive computational complexity, we present the Global Feature Modulation Layer (GFML). GFML associates features from different views by permuting the feature maps, enabling efficient modeling of long-range dependency. In addition, we also design the Local Feature Modulation Layer (LFML) and Feed-forward Layer (FFL) to capture local features and transform features into a compact representation. This way, our MixNet achieves effective LLIE with few model parameters and low computational complexity. We conducted extensive experiments on both synthetic and real-world datasets, and the comprehensive results demonstrate that our proposed method surpasses the performance of current state-of-the-art methods. The code will be available at \url{https://github.com/zzr-idam/MixNet}.
Hyperspectral band selection plays a pivotal role in remote sensing and image analysis, aiming to identify the most informative spectral bands while minimizing computational overhead. In this paper, we introduce a pioneering approach for hyperspectral band selection that offers an embedded solution, making it well-suited for resource-constrained or real-time applications. Our proposed method, embedded Hyperspectral Band Selection (EHBS), excels in selecting the best bands without the need for prior processing, seamlessly integrating with the downstream task model. This is achieved through the adaptation of the Stochastic Gates (STG) algorithm, originally designed for feature selection, for hyperspectral band selection in the context of image semantic segmentation and the integration of a dynamic optimizer, DoG, which removes the need for the required tuning the learning rate. To assess the performance of our method, we introduce a novel metric for evaluating band selection methods across different target numbers of selected bands quantified by the Area Under the Curve (AUC). We conduct experiments on two distinct semantic-segmentation hyperspectral benchmark datasets, demonstrating its superiority in terms of its resulting accuracy and its ease of use compared to many common and state-of-the-art methods. Furthermore, our contributions extend beyond the realm of hyperspectral band selection. The adaptability of our approach to other tasks, especially those involving grouped features, opens up promising avenues for broader applications within the realm of deep learning, such as feature selection for feature groups. The demonstrated success on the tested datasets and the potential for application to a variety of tasks underscore the value of our method as a substantial addition to the field of computer vision.
By combining natural language understanding and the generation capabilities and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented reasoning capabilities in the real world. However, the generated text often suffers from inaccurate grounding in the visual input, resulting in errors such as hallucinating nonexistent scene elements, missing significant parts of the scene, and inferring incorrect attributes and relationships between objects. To address these issues, we introduce a novel framework, ViGoR (Visual Grounding Through Fine-Grained Reward Modeling) that utilizes fine-grained reward modeling to significantly enhance the visual grounding of LVLMs over pre-trained baselines. This improvement is efficiently achieved using much cheaper human evaluations instead of full supervisions, as well as automated methods. We show the effectiveness of our approach through numerous metrics on several benchmarks. Additionally, we construct a comprehensive and challenging dataset specifically designed to validate the visual grounding capabilities of LVLMs. Finally, we plan to release our human annotation comprising approximately 16,000 images and generated text pairs with fine-grained evaluations to contribute to related research in the community.
Knowledge Graphs (KGs) play a pivotal role in advancing various AI applications, with the semantic web community's exploration into multi-modal dimensions unlocking new avenues for innovation. In this survey, we carefully review over 300 articles, focusing on KG-aware research in two principal aspects: KG-driven Multi-Modal (KG4MM) learning, where KGs support multi-modal tasks, and Multi-Modal Knowledge Graph (MM4KG), which extends KG studies into the MMKG realm. We begin by defining KGs and MMKGs, then explore their construction progress. Our review includes two primary task categories: KG-aware multi-modal learning tasks, such as Image Classification and Visual Question Answering, and intrinsic MMKG tasks like Multi-modal Knowledge Graph Completion and Entity Alignment, highlighting specific research trajectories. For most of these tasks, we provide definitions, evaluation benchmarks, and additionally outline essential insights for conducting relevant research. Finally, we discuss current challenges and identify emerging trends, such as progress in Large Language Modeling and Multi-modal Pre-training strategies. This survey aims to serve as a comprehensive reference for researchers already involved in or considering delving into KG and multi-modal learning research, offering insights into the evolving landscape of MMKG research and supporting future work.
In recent years, a range of neural network-based methods for image rendering have been introduced. For instance, widely-researched neural radiance fields (NeRF) rely on a neural network to represent 3D scenes, allowing for realistic view synthesis from a small number of 2D images. However, most NeRF models are constrained by long training and inference times. In comparison, Gaussian Splatting (GS) is a novel, state-of-theart technique for rendering points in a 3D scene by approximating their contribution to image pixels through Gaussian distributions, warranting fast training and swift, real-time rendering. A drawback of GS is the absence of a well-defined approach for its conditioning due to the necessity to condition several hundred thousand Gaussian components. To solve this, we introduce Gaussian Mesh Splatting (GaMeS) model, a hybrid of mesh and a Gaussian distribution, that pin all Gaussians splats on the object surface (mesh). The unique contribution of our methods is defining Gaussian splats solely based on their location on the mesh, allowing for automatic adjustments in position, scale, and rotation during animation. As a result, we obtain high-quality renders in the real-time generation of high-quality views. Furthermore, we demonstrate that in the absence of a predefined mesh, it is possible to fine-tune the initial mesh during the learning process.
Rainy weather will have a significant impact on the regular operation of the imaging system. Based on this premise, image rain removal has always been a popular branch of low-level visual tasks, especially methods using deep neural networks. However, most neural networks are but-branched, such as only using convolutional neural networks or Transformers, which is unfavourable for the multidimensional fusion of image features. In order to solve this problem, this paper proposes a dual-branch attention fusion network. Firstly, a two-branch network structure is proposed. Secondly, an attention fusion module is proposed to selectively fuse the features extracted by the two branches rather than simply adding them. Finally, complete ablation experiments and sufficient comparison experiments prove the rationality and effectiveness of the proposed method.
We present the Hourglass Diffusion Transformer (HDiT), an image generative model that exhibits linear scaling with pixel count, supporting training at high-resolution (e.g. $1024 \times 1024$) directly in pixel-space. Building on the Transformer architecture, which is known to scale to billions of parameters, it bridges the gap between the efficiency of convolutional U-Nets and the scalability of Transformers. HDiT trains successfully without typical high-resolution training techniques such as multiscale architectures, latent autoencoders or self-conditioning. We demonstrate that HDiT performs competitively with existing models on ImageNet $256^2$, and sets a new state-of-the-art for diffusion models on FFHQ-$1024^2$.