31 accepted papers
In range-based SLAM systems, localization accuracy depends on the quality of geometric maps. Sparse LiDAR scans and noisy depth from RGB-D sensors often yield incomplete or inaccurate reconstructions that degrade pose estimation. Appearance and semantic cues, readily available from onboard RGB and p
Current query-driven 3D understanding methods are constrained to static point clouds, limiting their ability to reason about dynamic scenes. To bridge this gap, we propose MORE-STEM, a unified framework for Long-Short MemOry REcall and Spatio-TEmporal Consistency Model in Query-Driven 3D/4D Point Cl
The rapid advancement of vision-language models (VLMs) in 3D domains has accelerated research in text-query-guided point cloud processing, though existing methods underperform in point-level segmentation due to inadequate 3D-text alignment that limits local feature-text context linking. To address t
Recently, large language models (LLMs) have been explored widely for 3D scene understanding. Among them, training-free approaches are gaining attention for their flexibility and generalization over training-based methods. However, they typically struggle with accuracy and efficiency in practical dep
We propose 3D-SLNR, a new and ultra-lightweight neural representation with outstanding performance for large-scale 3D mapping. The representation defines a global signed distance function (SDF) in near-surface space based on a set of band-limited local SDFs anchored at support points sampled from po…
Most existing visual-inertial odometry (VIO) initialization methods rely on accurate pre-calibrated extrinsic parameters. However, during long-term use, irreversible structural deformation caused by temperature changes, mechanical squeezing, etc. will cause changes in extrinsic parameters, especiall
Point cloud segmentation has a wide range of applications in autonomous driving, augmented reality and virtual reality. Multi-modal fusion strategies have received increasing attention in point cloud segmentation recently. Despite the success, existing methods usually generate unnecessary informatio…
Floorplan reconstruction provides structural priors essential for reliable indoor robot navigation and high-level scene understanding. However, existing approaches either require time-consuming offline processing with a complete map, or rely on expensive sensors and substantial computational resourc
Single-view 3D reconstruction is a fundamental problem in computer vision, having a significant impact on downstream tasks such as autonomous driving, virtual reality and augmented reality. However, existing single-view reconstruction methods are unable to reconstruct the regions outside the input f…
Existing multi-session visual simultaneous localization and mapping (SLAM) systems struggle severely to achieve robust localization and map merging under extreme viewpoint and illumination variations, particularly when handling completely opposite viewpoints and drastic day-night lighting changes. T
Generally, high-level features provide more geometrical information compared to point features, which can be exploited to further constrain motions. Planes are commonplace in man-made environments, offering an active means to reduce drift, due to their extensive spatial and temporal observability. T
Large Language Models (LLMs) are foundational in language technologies, particularly in information retrieval (IR). In this paper, we thoroughly explore the best practice of leveraging LLMs for query expansion. To this end, we introduce a training-free, straightforward yet effective framework called…
Planar structures, prevalent in man-made environments, can be observed by a camera for significant periods of time due to their large spatial presence. These structures provide strong planar regularities for Simultaneous Localization and Mapping (SLAM) systems, facilitating long-term navigation. The
The immense popularity of racket sports has fueled substantial demand in tactical analysis with broadcast videos. However, existing manual methods require laborious annotation, and recent attempts leveraging video perception models are limited to low-level annotations like ball trajectories, overloo…
Large-scale 3D mapping nowadays is a research hotspot in robotics. A greatly concerning issue is reconstructing high-accuracy maps in a hardware environment with limited memory. To address this problem, we propose a novel implicit neural mapping approach with higher accuracy and less memory. It firs
Feature-based point cloud registration algorithms have gained more attention recently for their high robustness. Outlier rejection is a key step of such algorithms. With the development of deep learning, some of the learning-based outlier rejection methods have been proposed and implemented in vario
In conversational search, the user’s real search intent for the current conversation turn is dependent on the previous conversation history. It is challenging to determine a good search query from the whole conversation context. To avoid the expensive re-training of the query encoder, most existing…
Depth estimation for single image using deep learning requires a large labelled depth dataset with various scenes for training. However, currently published omnidirectional depth datasets cover limited types of scenes and are not suitable for depth estimation for various real-world scenes. With the…
Multi-modal open-domain question answering typically requires evidence retrieval from databases across diverse modalities, such as images, tables, passages, etc. Even Large Language Models (LLMs) like GPT-4 fall short in this task. To enable LLMs to tackle the task in a zero-shot manner, we introduc…
Point and line features are complementary in Visual-Inertial Odometry (VIO) or Visual-Inertial Simultaneous Localization And Mapping (VI-SLAM) systems. The advantage of combining these two types of features relies on their proper weighting in the cost function, usually set by their uncertainty. Comp…
Man-made buildings exhibit structural regularity, which can provide strongly geometrical constraints for Visual-Inertial Odometry (VIO) systems. To make full use of the structural information, we propose a new structural regularity aided VIO with novel coordinate alignment and line triangulation und
Loop closure detection (LCD) is an essential module for simultaneous localization and mapping (SLAM), which can correct accumulated errors after long-term explorations. The widely used bag-of-words (BoW) model can not satisfy well the requirements of both low time consumption and high accuracy for a…
Weak texture and motion blur are always challenging problems for visual-inertial odometry (VIO) systems. To improve accuracy of VIO systems in the challenging scenes, we propose a point-line-based VIO system with novel feature hybrids and with novel predicting-matching for long line track. Point-lin
Line segment features become popular in SLAM community. Usually, line-based SLAM systems utilize local appearance descriptors for line segment tracking. However, traditional descriptor-based line segment tracking algorithms suffer from the problem that accuracy and speed cannot be possessed simultan…
We study the following learning problem with dependent data: Given a trajectory of length $n$ from a stationary Markov chain with $k$ states, the goal is to predict the distribution of the next state. For $3 \leq k \leq O(\sqrt{n})$, the optimal prediction risk in the Kullback-Leibler divergence is…
Graph matching, also known as network alignment, aims at recovering the latent vertex correspondence between two unlabeled, edge-correlated weighted graphs. To tackle this task, we propose a spectral method, GRAph Matching by Pairwise eigen-Alignments (GRAMPA), which first constructs a similarity ma…
Place recognition as one of the most significant requirements for long-term simultaneous localization and mapping (SLAM) has been developed rapidly in recent years. Also, deep learning is proved to be more capable than traditional methods to extract features under some complex environments. However,…
We propose a novel stereo visual SLAM framework considering both accuracy and speed at the same time. The framework makes full use of the advantages of key-feature-based multiple view geometry (MVG) and direct-based formulation. At the front-end, our system performs direct formulation and constant m…
Estimating properties of discrete distributions is a fundamental problem in statistical learning. We design the first unified, linear-time, competitive, property estimator that for a wide class of properties and for all underlying distributions uses just 2n samples to achieve the performance attaine…
Entropy estimation is one of the prototypical problems in distribution property testing. To consistently estimate the Shannon entropy of a distribution on $S$ elements with independent samples, the optimal sample complexity scales sublinearly with $S$ as $\Theta(\frac{S}{\log S})$ as shown by Valian…