Related papers: MGMapNet: Multi-Granularity Representation Learnin…
Remote sensing images captured from aerial perspectives often exhibit significant scale variations and complex backgrounds, posing challenges for salient object detection (SOD). Existing methods typically extract multi-level features at a…
High-definition (HD) map provides abundant and precise static environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomous driving system. In this paper, we present…
Three-dimensional (3D) shape recognition has drawn much research attention in the field of computer vision. The advances of deep learning encourage various deep models for 3D feature representation. For point cloud and multi-view data, two…
Video instance segmentation (VIS) is a new and critical task in computer vision. To date, top-performing VIS methods extend the two-stage Mask R-CNN by adding a tracking branch, leaving plenty of room for improvement. In contrast, we…
Point cloud completion aims to recover complete 3D geometry from partial observations caused by limited viewpoints and occlusions. Existing learning-based works, including 3D Convolutional Neural Network (CNN)-based, point-based, and…
Being data-driven is one of the most iconic properties of deep learning algorithms. The birth of ImageNet drives a remarkable trend of "learning from large-scale data" in computer vision. Pretraining on ImageNet to obtain rich universal…
Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. Mainstream methods (e.g., PCN and TopNet) use Multi-layer Perceptrons (MLPs) to directly process point clouds, which…
Autonomous driving requires the inference of actionable information such as detecting and classifying objects, and determining the drivable space. To this end, we present Multi-View LidarNet (MVLidarNet), a two-stage deep neural network for…
The analysis of 3D point clouds has diverse applications in robotics, vision and graphics. Processing them presents specific challenges since they are naturally sparse, can vary in spatial resolution and are typically unordered. Graph-based…
In autonomous driving, the high-definition (HD) map plays a crucial role in localization and planning. Recently, several methods have facilitated end-to-end online map construction in DETR-like frameworks. However, little attention has been…
Architectures that first convert point clouds to a grid representation and then apply convolutional neural networks achieve good performance for radar-based object detection. However, the transfer from irregular point cloud data to a dense…
We propose a novel approach for 3D shape completion by synthesizing multi-view depth maps. While previous work for shape completion relies on volumetric representations, meshes, or point clouds, we propose to use multi-view depth maps from…
The construction of online vectorized High-Definition (HD) maps is critical for downstream prediction and planning. Recent efforts have built strong baselines for this task, however, shapes and relations of instances in urban road systems…
Human instance matting aims to estimate an alpha matte for each human instance in an image, which is challenging as it easily fails in complex cases requiring disentangling mingled pixels belonging to multiple instances along hairy and thin…
Segmentation of three-dimensional (3D) point clouds is an important task for autonomous systems. However, success of segmentation algorithms depends greatly on the quality of the underlying point clouds (resolution, completeness etc.). In…
Autonomous vehicles rely on map information to understand the world around them. However, the creation and maintenance of offline high-definition (HD) maps remains costly. A more scalable alternative lies in online HD map construction,…
Point cloud based 3D deep model has wide applications in many applications such as autonomous driving, house robot, and so on. Inspired by the recent prompt learning in natural language processing, this work proposes a novel Multi-view…
The rapid development of spatial transcriptomics (ST) offers new opportunities to explore the gene expression patterns within the spatial microenvironment. Current research integrates pathological images to infer gene expression, addressing…
With the rapid advances of image editing techniques in recent years, image manipulation detection has attracted considerable attention since the increasing security risks posed by tampered images. To address these challenges, a novel…
Multimodal information processing has become increasingly important for enhancing image classification performance. However, the intricate and implicit dependencies across different modalities often hinder conventional methods from…