Related papers: 3SHNet: Boosting Image-Sentence Retrieval via Visu…

While self-supervised learning techniques are often used to mining implicit knowledge from unlabeled data via modeling multiple views, it is unclear how to perform effective representation learning in a complex and inconsistent context. To…

We propose an efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects. We first transform a 3D input volume into a 2D planar image using stereographic projection. We then present a shallow 2D…

Semantic scene completion is the task of producing a complete 3D voxel representation of volumetric occupancy with semantic labels for a scene from a single-view observation. We built upon the recent work of Song et al. (CVPR 2017), who…

Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neurel rendering methods as 3D…

High-resolution remote sensing (HRS) semantic segmentation extracts key objects from high-resolution coverage areas. However, objects of the same category within HRS images generally show significant differences in scale and shape across…

Three-dimensional feature extraction is a critical component of autonomous driving systems, where perception tasks such as 3D object detection, bird's-eye-view (BEV) semantic segmentation, and occupancy prediction serve as important…

This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…

Semantic segmentation and semantic edge detection can be seen as two dual problems with close relationships in computer vision. Despite the fast evolution of learning-based 3D semantic segmentation methods, little attention has been drawn…

In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images. To achieve high-quality images,…

Deep hashing techniques have emerged as the predominant approach for efficient image retrieval. Traditionally, these methods utilize pre-trained convolutional neural networks (CNNs) such as AlexNet and VGG-16 as feature extractors. However,…

Pixel-level 2D object semantic understanding is an important topic in computer vision and could help machine deeply understand objects (e.g. functionality and affordance) in our daily life. However, most previous methods directly train on…

Two factors have proven to be very important to the performance of semantic segmentation models: global context and multi-level semantics. However, generating features that capture both factors always leads to high computational complexity,…

We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is an Improved Guided Upsampling Module that can replace in toto the decoder part in common semantic segmentation…

Large imbalance often exists between the foreground points (i.e., objects) and the background points in outdoor LiDAR point clouds. It hinders cutting-edge detectors from focusing on informative areas to produce accurate 3D object detection…

Deep learning-based hyperspectral image super-resolution (SR) methods have achieved great success recently. However, most existing models can not effectively explore spatial information and spectral information between bands simultaneously,…

Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet current 3DSG construction methods suffer from semantic inconsistencies caused by noisy cross-image…

This study aims to address the problem of incomplete information in unimodal images for semantic segmentation and object detection tasks. Existing multimodal fusion methods suffer from limited capability in discriminative modeling of…

The main obstacle to weakly supervised semantic image segmentation is the difficulty of obtaining pixel-level information from coarse image-level annotations. Most methods based on image-level annotations use localization maps obtained from…

Deep learning algorithms have obtained great success in semantic segmentation of very high-resolution (VHR) images. Nevertheless, training these models generally requires a large amount of accurate pixel-wise annotations, which is very…

Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for autonomous driving. Recently, many studies have turned to…