Related papers: GLACE: Global Local Accelerated Coordinate Encodin…

Accurately rendering scenes with reflective surfaces remains a significant challenge in novel view synthesis, as existing methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) often misinterpret reflections as physical…

Exploiting 3D Gaussian Splatting (3DGS) with Contrastive Language-Image Pre-Training (CLIP) models for open-vocabulary 3D semantic understanding of indoor scenes has emerged as an attractive research focus. Existing methods typically attach…

Simultaneous Localization and Mapping (SLAM) is a critical task in robotics, enabling systems to autonomously navigate and understand complex environments. Current SLAM approaches predominantly rely on geometric cues for mapping and…

Visual localization is a key technique to a variety of applications, e.g., autonomous driving, AR/VR, and robotics. For these real applications, both efficiency and accuracy are important especially on edge devices with limited computing…

Simultaneous localization and mapping (SLAM) has achieved impressive performance in static environments. However, SLAM in dynamic environments remains an open question. Many methods directly filter out dynamic objects, resulting in…

We aim at accelerating super-resolution (SR) networks on large images (2K-8K). The large images are usually decomposed into small sub-images in practical usages. Based on this processing, we found that different image regions have different…

Multimodal learning aims to capture both shared and private information from multiple modalities. However, existing methods that project all modalities into a single latent space for fusion often overlook the asynchronous, multi-level…

We introduce a novel problem, i.e., the localization of an input image within a multi-modal reference map represented by a database of 3D scene graphs. These graphs comprise multiple modalities, including object-level point clouds, images,…

Worldwide Geo-localization aims to pinpoint the precise location of images taken anywhere on Earth. This task has considerable challenges due to immense variation in geographic landscapes. The image-to-image retrieval-based approaches fail…

Recent advancements in large-scale pretraining in natural language processing have enabled pretrained vision-language models such as CLIP to effectively align images and text, significantly improving performance in zero-shot image…

We propose a novel object-augmented RGB-D SLAM system that is capable of constructing a consistent object map and performing relocalisation based on centroids of objects in the map. The approach aims to overcome the view dependence of…

Accurate visual re-localization is very critical to many artificial intelligence applications, such as augmented reality, virtual reality, robotics and autonomous driving. To accomplish this task, we propose an integrated visual…

Language-augmented scene representations hold great promise for large-scale robotics applications such as search-and-rescue, smart cities, and mining. Many of these scenarios are time-sensitive, requiring rapid scene encoding while also…

Self-supervised learning (SSL) has emerged as a central paradigm for training foundation models by leveraging large-scale unlabeled datasets, often producing representations with strong generalization capabilities. These models are…

Camera-based 3D Semantic Scene Completion (SSC) is a critical task in autonomous driving systems, assessing voxel-level geometry and semantics for holistic scene perception. While existing voxel-based and plane-based SSC methods have…

Visual autoregressive (VAR) models have recently emerged as a promising alternative for image generation, offering stable training, non-iterative inference, and high-fidelity synthesis through next-scale prediction. This encourages the…

Visual-based recognition, e.g., image classification, object detection, etc., is a long-standing challenge in computer vision and robotics communities. Concerning the roboticists, since the knowledge of the environment is a prerequisite for…

Subspace clustering has become widely adopted for the unsupervised analysis of hyperspectral images (HSIs). Recent model-aware deep subspace clustering methods often use a two-stage framework, involving the calculation of a…

Compared with previous 3D reconstruction methods like Nerf, recent Generalizable 3D Gaussian Splatting (G-3DGS) methods demonstrate impressive efficiency even in the sparse-view setting. However, the promising reconstruction performance of…

Real-scene image super-resolution aims to restore real-world low-resolution images into their high-quality versions. A typical RealSR framework usually includes the optimization of multiple criteria which are designed for different image…