相关论文: HoHoNet: 360 Indoor Holistic Understanding with La…

The low-level spatial detail information and high-level semantic abstract information are both essential to the semantic segmentation task. The features extracted by the deep network can obtain rich semantic information, while a lot of…

Multimodal image registration is a fundamental task and a prerequisite for downstream cross-modal analysis. Despite recent progress in shared feature extraction and multi-scale architectures, two key limitations remain. First, some methods…

Haze usually leads to deteriorated images with low contrast, color shift and structural distortion. We observe that many deep learning based models exhibit exceptional performance on removing homogeneous haze, but they usually fail to…

Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses or remote sensing. Many of these applications require fast inference over large input resolutions on affordable or…

Forecasting complex system dynamics, particularly for long-term predictions, is persistently hindered by error accumulation and computational burdens. This study presents RefreshNet, a multiscale framework developed to overcome these…

Mapping Low Dynamic Range (LDR) images with different exposures to High Dynamic Range (HDR) remains nontrivial and challenging on dynamic scenes due to ghosting caused by object motion or camera jitting. With the success of Deep Neural…

Recent advances in artificial intelligence (AI), in particular foundation models, have improved the state of the art in many application domains including geosciences. Some specific problems, however, could not benefit from this progress…

Modern deep neural networks are powerful and widely applicable models that extract task-relevant information through multi-level abstraction. Their cross-domain success, however, is often achieved at the expense of computational cost, high…

Robust point cloud registration is a fundamental task in 3D computer vision and geometric deep learning, essential for applications such as large-scale 3D reconstruction, augmented reality, and scene understanding. However, the performance…

Adaptation of foundation models using low-rank methods is a widespread approach. Another way to adapt these models is to employ orthogonal fine-tuning methods, which are less time and memory efficient despite their good generalization…

This paper presents EHSNet, a new end-to-end segmentation network designed for the holistic learning of large-size remote sensing image semantic segmentation (LRISS). Large-size remote sensing images (LRIs) can lead to GPU memory exhaustion…

Recent NeRF methods on large-scale scenes have underlined the importance of scene decomposition for scalable NeRFs. Although achieving reasonable scalability, there are several critical problems remaining unexplored, i.e., learnable…

In recent years, sparse voxel-based methods have become the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs. Nevertheless, being oblivious to the underlying geometry, voxel-based methods…

This work presents FG-Net, a general deep learning framework for large-scale point clouds understanding without voxelizations, which achieves accurate and real-time performance with a single NVIDIA GTX 1080 GPU. First, a novel noise and…

In this paper we introduce a novel neural network architecture based on Fast Hough Transform layer. The layer of this type allows our neural network to accumulate features from linear areas across the entire image instead of local areas. We…

In the realm of intelligent maritime navigation, object detection from a shipborne perspective is paramount. Despite the criticality, the paucity of maritime-specific data impedes the deployment of sophisticated visual perception…

We present Im2Pano3D, a convolutional neural network that generates a dense prediction of 3D structure and a probability distribution of semantic labels for a full 360 panoramic view of an indoor scene when given only a partial observation…

We propose HookNet, a semantic segmentation model for histopathology whole-slide images, which combines context and details via multiple branches of encoder-decoder convolutional neural networks. Concentricpatches at multiple resolutions…

Hyperspectral Image (HSI) classification based on deep learning has been an attractive area in recent years. However, as a kind of data-driven algorithm, deep learning method usually requires numerous computational resources and…

3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient geometry awareness of room layout with the only latitude of boundaries or…