Visual grounding (VG) aims to localize target objects in an image based on natural language descriptions. In this paper, we propose AerialVG, a new task focusing on visual grounding from aerial views. Compared to traditional VG, AerialVG poses new challenges, \emph{e.g.}, appearance-based grounding is insufficient to distinguish among multiple visually similar objects, and positional relations should be emphasized. Besides, existing VG models struggle when applied to aerial imagery, where high-resolution images cause significant difficulties. To address these challenges, we introduce the first AerialVG dataset, consisting of 5K real-world aerial images, 50K manually annotated descriptions, and 103K objects. Particularly, each annotation in AerialVG dataset contains multiple target objects annotated with relative spatial relations, requiring models to perform comprehensive spatial reasoning. Furthermore, we propose an innovative model especially for the AerialVG task, where a Hierarchical Cross-Attention is devised to focus on target regions, and a Relation-Aware Grounding module is designed to infer positional relations. Experimental results validate the effectiveness of our dataset and method, highlighting the importance of spatial reasoning in aerial visual grounding. The code and dataset will be released.

Implicit neural SLAM has achieved remarkable progress recently. Nevertheless, existing methods face significant challenges in non-ideal scenarios, such as motion blur or lighting variation, which often leads to issues like convergence failures, localization drifts, and distorted mapping. To address these challenges, we propose EN-SLAM, the first event-RGBD implicit neural SLAM framework, which effectively leverages the high rate and high dynamic range advantages of event data for tracking and mapping. Specif-ically, EN-SLAM proposes a differentiable CRF (Camera Response Function) rendering technique to generate dis-tinct RGB and event camera data via a shared radiance field, which is optimized by learning a unified implicit representation with the captured event and RGBD supervision. Moreover, based on the temporal difference property of events, we propose a temporal aggregating optimization strategy for the event joint tracking and global bundle adjustment, capitalizing on the consecutive difference constraints of events, significantly enhancing tracking accuracy and robustness. Finally, we construct the simulated dataset DEV-Indoors and real captured dataset DEV-Reals containing 6 scenes, 17 sequences with practical motion blur and lighting changes for evaluations. Experimental results show that our method outperforms the SOTA methods in both tracking ATE and mapping ACC with a real-time 17 FPS in various challenging environments. Project page: https://delinqu.github.io/EN-SLAM.

In this paper, we introduce GS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better bal-ance between efficiency and accuracy. Compared to recent SLAM methods employing neural implicit representations, our method utilizes a real-time differentiable splatting ren-dering pipeline that offers significant speedup to map opti-mization and RGB-D rendering. Specifically, we propose an adaptive expansion strategy that adds new or deletes noisy 3D Gaussians in order to efficiently reconstruct new observed scene geometry and improve the mapping of pre-viously observed areas. This strategy is essential to ex-tend 3D Gaussian representation to reconstruct the whole scene rather than synthesize a static object in existing meth-ods. Moreover, in the pose tracking process, an effective coarse-to-fine technique is designed to select reliable 3D Gaussian representations to optimize camera pose, resulting in runtime reduction and robust estimation. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets. Project page: https://gs-slam.github.io/.

Vision is an important source of information for underwater observations, but underwater images commonly suffer severe visual degradation due to the complexity of the underwater imaging environment and wavelength-dependent absorption effects. There is an urgent need for underwater image enhancement techniques to improve the visual quality of underwater images. Due to the scarcity of high-quality paired training samples, underwater image enhancement based on deep learning has never achieved success similar to other vision tasks. Instead of learning complicated distortion-to-clear mappings with deep networks, we design a template-free color transfer learning framework for predicting transfer parameters, which are more easily captured and described. In addition, we add attention-driven modules to learn differentiated transfer parameters for more flexible and robust enhancement. We verify the effectiveness of our method on multiple publicly available datasets and show its efficiency in enhancing high-resolution images. The source code and the trained models are available on the project homepage: https://trentqq.github.io/TCTL-Net.html.

Accurately retrieving ocean interior parameters from remote sensing observations is essential for ocean and climate studies because direct observations are sparse and costly. Furthermore, high-resolution structure of seawater properties is critical for understanding the oceanic processes and changes on multiple scales. Here, we designed a new method based on a deep neural network to retrieve subsurface temperature anomaly (STA) and subsurface salinity anomaly (SSA) in the Pacific Ocean at high (1/4°) and super (1/12°) horizontal resolution. We utilized multisource satellite-observed sea surface data (e.g., sea level, temperature, salinity, and wind vector) as inputs. The results revealed that our model retrieved the high- and super-resolution STA/SSA with high accuracy, and the model was reliable in a wide range of depths (near surface to 4000 m) and times (all months in 2014). Regarding the high-resolution STA (SSA) estimation, the average coefficient of determination ($R^{2}$) was 0.984 (0.966), and the average root-mean-squared error (RMSE) was 0.068 °C (0.016 psu). For the super-resolution STA, the average$R^{2}$was 0.988 and RMSE was 0.093 °C. Here, we established an effective technique that improved the resolution and accuracy of estimating the ocean interior parameters from satellite observation. The new technique provides some new insights into oceanic observation and dynamics.