arXiv subjects

Giseop Kim

Publications and source records attributed to Giseop Kim.

At least 19 recordsLinked to original sources

arXiv2026

LT-Mem: Volatility-Aware Spatio-Temporal Memory for Lifelong Scene Understanding

Long-term robot operation in evolving environments requires object-level understanding that persists across repeated revisits. Existing systems either overwrite history to maintain an up-to-date map or store semantic snapshots without consistent cross-session object identity, resulting in temporal amnesia: the systematic loss of object history that prevents answering queries such as "Where has the green chair been across all sessions?" We propose LT-Mem, a volatility-aware memory evolution framework that unifies spatially aligned instance-level 3D perception with volatility-conditioned temporal reasoning. First, a multi-session SLAM backbone provides spatially aligned per-object observations across sessions. Second, a reasoning layer governs how object memory evolves: deterministic evidence scoring preserves cross-session identity, and a volatility-aware policy selects among overwrite, hold, and multi-hypothesis actions based on each object's dynamics. Third, the resulting Tri-Memory structure (Live, Delta, Meta) preserves both current states and event histories, enabling longitudinal object-centric reasoning. We further introduce LT-VQA, a dataset and evaluation suite comprising multi-session recordings, persistent identity annotations, and temporal QA pairs. Experiments show that LT-Mem consistently outperforms baselines across all metrics while consuming an order of magnitude fewer tokens, and ablations confirm that gains are driven by the structured memory architecture rather than LLM capacity.

cs.RO↗

arXiv2026

Are Visual Place Recognition Models Recognizing Places or Conditions? Distractor-Augmented Evaluation and Condition Suppression

Long-term Visual Place Recognition (VPR) is typically evaluated by matching queries from one condition against a database from another. Crowdsourced map databases, however, may mix conditions and include images that resemble the query in condition but depict different places. In the presence of these distractors, a method may retrieve by condition similarity rather than place identity. We argue that this susceptibility arises because the discriminability of VPR methods allows them to encode information such as illumination, weather, and seasonal appearance in their descriptors. We therefore introduce Distractor-Augmented Recall (DAR) to isolate and quantify the effect of distractors, and propose condition suppression to remove condition information from VPR descriptors. Across eleven methods and six datasets, method rankings under DAR@1 differ from those under Recall@1 (R@1), while applying INLP and LEACE as condition suppression methods generally improves DAR@1 without reducing R@1. Thus, distractor robustness is distinct from standard retrieval performance and can be improved by suppressing condition information.

cs.RO↗

arXiv2026

Mag4D-SLAM Dataset: A Repeated-Traversal Multi-Modal 4D Geomagnetic Dataset for Localization and Mapping

Geomagnetic sensing offers an infrastructure-free, absolute orientation reference that is robust to GNSS denial and visual degradation, yet no large-scale outdoor robotics dataset supports its systematic study in SLAM. Existing magnetic datasets are confined to small-scale indoor environments and lack the synchronized multi-modal sensing, repeated-traversal structure, and high-precision 6-DoF ground truth required for geomagnetic SLAM research. We present Mag4D-SLAM, the first large-scale outdoor geomagnetic SLAM dataset. It comprises 14 sequences totaling over 18 km of synchronized LiDAR, camera, IMU, tri-axis magnetometer, and GNSS measurements with SE(3) ground-truth poses, collected along structured campus trajectories under paired day/night conditions in both forward and reverse directions. Through repeated-traversal experiments, we analyze three core properties: magnetic field repeatability across different recording sessions (daytime and nighttime), drift-free global heading estimation, and location-discriminative magnetic signatures for cross-session place recognition. Mag4D-SLAM is designed to support research on yaw drift mitigation, magnetic loop closure, and long-term localization and to open new research questions on how geomagnetic sensing can complement visual and LiDAR modalities or provide a fallback cue under illumination changes, structural repetition, and GNSS-denied long-term operation.

cs.RO↗

arXiv2026

Self-supervised Geometry Reasoning for LiDAR Simultaneous Localization and Mapping

LiDAR simultaneous localization and mapping (SLAM) relies on local geometric quantities such as covariances, correspondences, and surface structures. However, most existing pipelines rely on hand-crafted estimates of local geometry and use them as fixed inputs to LiDAR SLAM, which can make the estimated local geometry noisy and unstable in sparse regions of a point cloud or when using low-resolution LiDAR. To address this issue, this paper introduces a self-supervised framework that learns an explicit symbolic representation of local geometry and uses it to improve LiDAR SLAM recursively. Specifically, each point is represented as a Gaussian distribution, allowing local geometry to be described by a covariance. Without dense geometry labels or ground-truth poses, the framework learns by maximizing the likelihood of local geometry, with self-supervision derived from consistency relations over symbolic geometric representations, including predicted covariances, correspondences, and trajectory from SLAM. The learned geometry is then fed back into LiDAR SLAM, forming a reciprocal loop in which improved geometry enhances localization and mapping, and improved localization provides cleaner supervision for subsequent geometry reasoning. This framework is backend-agnostic and can be plugged into existing LiDAR SLAM pipelines without architectural changes. Experiments on KITTI under varying LiDAR resolutions show that the proposed method improves both odometry and global registration.

cs.RO↗

arXiv2026

Learning Point Cloud Geometry as a Statistical Manifold: Theory and Practice

Point clouds are a fundamental representation for robotic perception tasks such as localization, mapping, and object pose estimation. However, LiDAR-acquired point clouds are inherently sparse and non-uniform, providing incomplete observations of the underlying scene geometry. This makes reliable geometric reasoning challenging and degrades downstream perception performance. Existing approaches attempt to compensate for these limitations by estimating local geometry, but often rely on hand-crafted statistics or end-to-end supervised learning, which can suffer from limited scalability or require large amounts of accurately labeled data. To address these challenges, we explicitly model point cloud geometry under a principled mathematical formulation. We represent local geometry as a statistical manifold induced by a family of Gaussian distributions, where each point is associated with a Gaussian capturing its local geometric structure. Based on this formulation, we introduce Point-to-Ellipsoid (POLI), a deep neural estimator that predicts per-point Gaussian geometry. POLI learns a mapping from point cloud observations to their underlying geometry in a self-supervised manner, removing the need for labeled data while preserving strong geometric inductive biases. The resulting representation integrates seamlessly into existing robotic perception pipelines without architectural modifications. Extensive experiments show that POLI enables accurate and robust geometry estimation and consistently improves performance across diverse robotic perception tasks.

cs.RO↗

arXiv2026

MR.ScaleMaster: Scale-Consistent Collaborative Mapping from Crowd-Sourced Monocular Videos

Crowd-sourced cooperative mapping from monocular cameras promises scalable 3D reconstruction without specialized sensors, yet remains hindered by two scale-specific failure modes: abrupt scale collapse from false-positive loop closures in repetitive environments, and gradual scale drift over long trajectories and per-robot scale ambiguity that prevent direct multi-session fusion. We present MR$.$ScaleMaster, a cooperative mapping system for crowd-sourced monocular videos that addresses both failure modes. MR$.$ScaleMaster introduces three key mechanisms. First, a Scale Collapse Alarm rejects spurious loop closures before they corrupt the pose graph. Second, a Sim(3) anchor node formulation generalizes the classical SE(3) framework to explicitly estimate per-session scale, resolving per-robot scale ambiguity and enforcing global scale consistency. Third, a modular, open-source, plug-and-play interface enables any monocular reconstruction model to integrate without backend modification. On KITTI sequences with up to 15 agents, the Sim(3) formulation achieves a 7.2x ATE reduction over the SE(3) baseline, and the alarm rejects all false-positive loops while preserving every valid constraint. We further demonstrate heterogeneous multi-robot dense mapping fusing MASt3R-SLAM, pi3, and VGGT-SLAM 2.0 within a single unified map.

cs.RO↗

arXiv2026

Have We Mastered Scale in Deep Monocular Visual SLAM? The ScaleMaster Dataset and Benchmark

Recent advances in deep monocular visual Simultaneous Localization and Mapping (SLAM) have achieved impressive accuracy and dense reconstruction capabilities, yet their robustness to scale inconsistency in large-scale indoor environments remains largely unexplored. Existing benchmarks are limited to room-scale or structurally simple settings, leaving critical issues of intra-session scale drift and inter-session scale ambiguity insufficiently addressed. To fill this gap, we introduce the ScaleMaster Dataset, the first benchmark explicitly designed to evaluate scale consistency under challenging scenarios such as multi-floor structures, long trajectories, repetitive views, and low-texture regions. We systematically analyze the vulnerability of state-of-the-art deep monocular visual SLAM systems to scale inconsistency, providing both quantitative and qualitative evaluations. Crucially, our analysis extends beyond traditional trajectory metrics to include a direct map-to-map quality assessment using metrics like Chamfer distance against high-fidelity 3D ground truth. Our results reveal that while recent deep monocular visual SLAM systems demonstrate strong performance on existing benchmarks, they suffer from severe scale-related failures in realistic, large-scale indoor environments. By releasing the ScaleMaster dataset and baseline results, we aim to establish a foundation for future research toward developing scale-consistent and reliable visual SLAM systems.

cs.RO↗

arXiv2026

LAMP: Implicit Language Map for Robot Navigation

Recent advances in vision-language models have made zero-shot navigation feasible, enabling robots to follow natural language instructions without requiring labeling. However, existing methods that explicitly store language vectors in grid or node-based maps struggle to scale to large environments due to excessive memory requirements and limited resolution for fine-grained planning. We introduce LAMP (Language Map), a novel neural language field-based navigation framework that learns a continuous, language-driven map and directly leverages it for fine-grained path generation. Unlike prior approaches, our method encodes language features as an implicit neural field rather than storing them explicitly at every location. By combining this implicit representation with a sparse graph, LAMP supports efficient coarse path planning and then performs gradient-based optimization in the learned field to refine poses near the goal. This coarse-to-fine pipeline, language-driven, gradient-guided optimization is the first application of an implicit language map for precise path generation. This refinement is particularly effective at selecting goal regions not directly observed by leveraging semantic similarities in the learned feature space. To further enhance robustness, we adopt a Bayesian framework that models embedding uncertainty via the von Mises-Fisher distribution, thereby improving generalization to unobserved regions. To scale to large environments, LAMP employs a graph sampling strategy that prioritizes spatial coverage and embedding confidence, retaining only the most informative nodes and substantially reducing computational overhead. Our experimental results, both in NVIDIA Isaac Sim and on a real multi-floor building, demonstrate that LAMP outperforms existing explicit methods in both memory efficiency and fine-grained goal-reaching accuracy.

cs.RO↗

arXiv2026

Inlier-Centric Post-Training Quantization for Object Detection Models

Object detection is pivotal in computer vision, yet its immense computational demands make deployment slow and power-hungry, motivating quantization. However, task-irrelevant morphologies such as background clutter and sensor noise induce redundant activations (or anomalies). These anomalies expand activation ranges and skew activation distributions toward task-irrelevant responses, complicating bit allocation and weakening the preservation of informative features. Without a clear criterion to distinguish anomalies, suppressing them can inadvertently discard useful information. To address this, we present InlierQ, an inlier-centric post-training quantization approach that separates anomalies from informative inliers. InlierQ computes gradient-aware volume saliency scores, classifies each volume as an inlier or anomaly, and fits a posterior distribution over these scores using the Expectation-Maximization (EM) algorithm. This design suppresses anomalies while preserving informative features. InlierQ is label-free, drop-in, and requires only 64 calibration samples. Experiments on the COCO and nuScenes benchmarks show consistent reductions in quantization error for camera-based (2D and 3D) and LiDAR-based (3D) object detection.

cs.CV↗

arXiv2025

TRAN-D: 2D Gaussian Splatting-based Sparse-view Transparent Object Depth Reconstruction via Physics Simulation for Scene Update

Understanding the 3D geometry of transparent objects from RGB images is challenging due to their inherent physical properties, such as reflection and refraction. To address these difficulties, especially in scenarios with sparse views and dynamic environments, we introduce TRAN-D, a novel 2D Gaussian Splatting-based depth reconstruction method for transparent objects. Our key insight lies in separating transparent objects from the background, enabling focused optimization of Gaussians corresponding to the object. We mitigate artifacts with an object-aware loss that places Gaussians in obscured regions, ensuring coverage of invisible surfaces while reducing overfitting. Furthermore, we incorporate a physics-based simulation that refines the reconstruction in just a few seconds, effectively handling object removal and chain-reaction movement of remaining objects without the need for rescanning. TRAN-D is evaluated on both synthetic and real-world sequences, and it consistently demonstrated robust improvements over existing GS-based state-of-the-art methods. In comparison with baselines, TRAN-D reduces the mean absolute error by over 39% for the synthetic TRansPose sequences. Furthermore, despite being updated using only one image, TRAN-D reaches a {\delta} < 2.5 cm accuracy of 48.46%, over 1.5 times that of baselines, which uses six images. Code and more results are available at https://jeongyun0609.github.io/TRAN-D/.

cs.RO↗

arXiv2025

Streaming Dense Voxel Representations for 3D Occupancy Prediction

In this paper, we explore dense voxel streaming for accurate and efficient 3D occupancy prediction. While dense voxel representations offer fine-grained spatial details and streaming paradigm enables efficient temporal processing, naively combining the two introduces key challenges: (i) warping-induced distortions caused by interpolation used for temporal alignment, and (ii) degraded dynamic object representations due to motion misalignment and detail loss in image-to-voxel projection. To address these, we propose StreamOcc, a novel framework that utilizes two aggregation strategies. Specifically, it first refines propagated voxel features to reduce warping artifacts before temporal accumulation, and then selectively injects instance-level query features encoding dynamic-object semantics into the corresponding occupied voxel regions, preserving temporally consistent modeling while strengthening dynamic object representations. Unlocking effective dense voxel streaming, StreamOcc achieves state-of-the-art performance on SurroundOcc-benchmark and Occ3D-nuScenes under real-time constraints, outperforming the prior best methods by +1.3/2.5 and +1.5/2.0 in (overall/dynamic object) mIoU, respectively, while running at 83.3 ms per frame with only 2.8 GB of memory. The project page is available at https://moonseokha.github.io/StreamOcc/.

cs.CV↗

arXiv2025

Ephemerality meets LiDAR-based Lifelong Mapping

Lifelong mapping is crucial for the long-term deployment of robots in dynamic environments. In this paper, we present ELite, an ephemerality-aided LiDAR-based lifelong mapping framework which can seamlessly align multiple session data, remove dynamic objects, and update maps in an end-to-end fashion. Map elements are typically classified as static or dynamic, but cases like parked cars indicate the need for more detailed categories than binary. Central to our approach is the probabilistic modeling of the world into two-stage $\textit{ephemerality}$, which represent the transiency of points in the map within two different time scales. By leveraging the spatiotemporal context encoded in ephemeralities, ELite can accurately infer transient map elements, maintain a reliable up-to-date static map, and improve robustness in aligning the new data in a more fine-grained manner. Extensive real-world experiments on long-term datasets demonstrate the robustness and effectiveness of our system. The source code is publicly available for the robotics community: https://github.com/dongjae0107/ELite.

cs.RO↗

arXiv2024

Addressing Diverging Training Costs using BEVRestore for High-resolution Bird's Eye View Map Construction

Recent advancements in Bird's Eye View (BEV) fusion for map construction have demonstrated remarkable mapping of urban environments. However, their deep and bulky architecture incurs substantial amounts of backpropagation memory and computing latency. Consequently, the problem poses an unavoidable bottleneck in constructing high-resolution (HR) BEV maps, as their large-sized features cause significant increases in costs including GPU memory consumption and computing latency, named diverging training costs issue. Affected by the problem, most existing methods adopt low-resolution (LR) BEV and struggle to estimate the precise locations of urban scene components like road lanes, and sidewalks. As the imprecision leads to risky motion planning like collision avoidance, the diverging training costs issue has to be resolved. In this paper, we address the issue with our novel BEVRestore mechanism. Specifically, our proposed model encodes the features of each sensor to LR BEV space and restores them to HR space to establish a memory-efficient map constructor. To this end, we introduce the BEV restoration strategy, which restores aliasing, and blocky artifacts of the up-scaled BEV features, and narrows down the width of the labels. Our extensive experiments show that the proposed mechanism provides a plug-and-play, memory-efficient pipeline, enabling an HR map construction with a broad BEV scope.

cs.CV↗

arXiv2024

Narrowing your FOV with SOLiD: Spatially Organized and Lightweight Global Descriptor for FOV-constrained LiDAR Place Recognition

We often encounter limited FOV situations due to various factors such as sensor fusion or sensor mount in real-world robot navigation. However, the limited FOV interrupts the generation of descriptions and impacts place recognition adversely. Therefore, we suffer from correcting accumulated drift errors in a consistent map using LiDAR-based place recognition with limited FOV. Thus, in this paper, we propose a robust LiDAR-based place recognition method for handling narrow FOV scenarios. The proposed method establishes spatial organization based on the range-elevation bin and azimuth-elevation bin to represent places. In addition, we achieve a robust place description through reweighting based on vertical direction information. Based on these representations, our method enables addressing rotational changes and determining the initial heading. Additionally, we designed a lightweight and fast approach for the robot's onboard autonomy. For rigorous validation, the proposed method was tested across various LiDAR place recognition scenarios (i.e., single-session, multi-session, and multi-robot scenarios). To the best of our knowledge, we report the first method to cope with the restricted FOV. Our place description and SLAM codes will be released. Also, the supplementary materials of our descriptor are available at \texttt{\url{https://sites.google.com/view/lidar-solid}}.

cs.RO↗

arXiv2024

HeLiPR: Heterogeneous LiDAR Dataset for inter-LiDAR Place Recognition under Spatiotemporal Variations

Place recognition is crucial for robot localization and loop closure in simultaneous localization and mapping (SLAM). Light Detection and Ranging (LiDAR), known for its robust sensing capabilities and measurement consistency even in varying illumination conditions, has become pivotal in various fields, surpassing traditional imaging sensors in certain applications. Among various types of LiDAR, spinning LiDARs are widely used, while non-repetitive scanning patterns have recently been utilized in robotics applications. Some LiDARs provide additional measurements such as reflectivity, Near Infrared (NIR), and velocity from Frequency modulated continuous wave (FMCW) LiDARs. Despite these advances, there is a lack of comprehensive datasets reflecting the broad spectrum of LiDAR configurations for place recognition. To tackle this issue, our paper proposes the HeLiPR dataset, curated especially for place recognition with heterogeneous LiDARs, embodying spatiotemporal variations. To the best of our knowledge, the HeLiPR dataset is the first heterogeneous LiDAR dataset supporting inter-LiDAR place recognition with both non-repetitive and spinning LiDARs, accommodating different field of view (FOV)s and varying numbers of rays. The dataset covers diverse environments, from urban cityscapes to high-dynamic freeways, over a month, enhancing adaptability and robustness across scenarios. Notably, HeLiPR includes trajectories parallel to MulRan sequences, making it valuable for research in heterogeneous LiDAR place recognition and long-term studies. The dataset is accessible at https://sites.google.com/view/heliprdataset.

cs.RO↗

arXiv2023

BroadBEV: Collaborative LiDAR-camera Fusion for Broad-sighted Bird's Eye View Map Construction

A recent sensor fusion in a Bird's Eye View (BEV) space has shown its utility in various tasks such as 3D detection, map segmentation, etc. However, the approach struggles with inaccurate camera BEV estimation, and a perception of distant areas due to the sparsity of LiDAR points. In this paper, we propose a broad BEV fusion (BroadBEV) that addresses the problems with a spatial synchronization approach of cross-modality. Our strategy aims to enhance camera BEV estimation for a broad-sighted perception while simultaneously improving the completion of LiDAR's sparsity in the entire BEV space. Toward that end, we devise Point-scattering that scatters LiDAR BEV distribution to camera depth distribution. The method boosts the learning of depth estimation of the camera branch and induces accurate location of dense camera features in BEV space. For an effective BEV fusion between the spatially synchronized features, we suggest ColFusion that applies self-attention weights of LiDAR and camera BEV features to each other. Our extensive experiments demonstrate that BroadBEV provides a broad-sighted BEV perception with remarkable performance gains.

cs.CV↗

arXiv2023

ORORA: Outlier-Robust Radar Odometry

Radar sensors are emerging as solutions for perceiving surroundings and estimating ego-motion in extreme weather conditions. Unfortunately, radar measurements are noisy and suffer from mutual interference, which degrades the performance of feature extraction and matching, triggering imprecise matching pairs, which are referred to as outliers. To tackle the effect of outliers on radar odometry, a novel outlier-robust method called \textit{ORORA} is proposed, which is an abbreviation of \textit{Outlier-RObust RAdar odometry}. To this end, a novel decoupling-based method is proposed, which consists of graduated non-convexity~(GNC)-based rotation estimation and anisotropic component-wise translation estimation~(A-COTE). Furthermore, our method leverages the anisotropic characteristics of radar measurements, each of whose uncertainty along the azimuthal direction is somewhat larger than that along the radial direction. As verified in the public dataset, it was demonstrated that our proposed method yields robust ego-motion estimation performance compared with other state-of-the-art methods. Our code is available at https://github.com/url-kaist/outlier-robust-radar-odometry.

cs.RO↗

arXiv2022

OpenStreetMap-based LiDAR Global Localization in Urban Environment without a Prior LiDAR Map

Using publicly accessible maps, we propose a novel vehicle localization method that can be applied without using prior light detection and ranging (LiDAR) maps. Our method generates OSM descriptors by calculating the distances to buildings from a location in OpenStreetMap at a regular angle, and LiDAR descriptors by calculating the shortest distances to building points from the current location at a regular angle. Comparing the OSM descriptors and LiDAR descriptors yields a highly accurate vehicle localization result. Compared to methods that use prior LiDAR maps, our method presents two main advantages: (1) vehicle localization is not limited to only places with previously acquired LiDAR maps, and (2) our method is comparable to LiDAR map-based methods, and especially outperforms the other methods with respect to the top one candidate at KITTI dataset sequence 00.

cs.RO↗