arXiv subjects

Sungho Moon

Publications and source records attributed to Sungho Moon.

8 recordsLinked to original sources

arXiv2026

RobOralScan: Learning Active Intraoral Scanning for Robotic Dental Reconstruction

Intraoral scanning is widely used for digital optical impressions in prosthodontic, implant, and orthodontic treatment, but full-arch and long-span scanning remain labor-intensive tasks with limited automation. In the confined oral cavity, operators must continuously adjust scanner motion while accumulating narrow field-of-view observations, making reconstruction quality sensitive to missing tooth surfaces and operator workload. We propose RobOralScan, which, to the best of our knowledge, is the first reinforcement learning (RL)-based pipeline for robotic automatic intraoral scanning. RobOralScan introduces a geometric memory-based observation space that accumulates partial scan observations into a tri-state geometric representation, allowing the policy to reason over scan history and insufficiently observed regions. It further introduces tooth-wise coverage learning, combining coverage-aware reward signals and a progressive training scheme to improve global reconstruction coverage while reducing uneven coverage across individual teeth. The learned policy selects relative scanner motions from accumulated geometric memory and robot proprioception for closed-loop scan control within the oral workspace. RobOralScan achieves a Chamfer Distance of 0.00838, an average coverage of 92.58%, a lower-tail per-tooth coverage of 88.45%, and a normalized AUC of 0.6674, completing the scan criterion in 8 of 10 evaluation episodes. Furthermore, zero-shot sim-to-real experiments demonstrate its practical feasibility on a physical robot-scanner setup.

cs.RO↗

arXiv2026

OffloadFS: Leveraging Disaggregated Storage for Computation Offloading

Disaggregated storage systems improve resource utilization and enable independent scaling of storage and compute resources by separating storage resources from computing resources in data centers. NVMe over fabrics (NVMeoF) is a key technology that underpins the functionality and benefits of disaggregated storage systems. While NVMeoF inherently possesses substantial computing and memory capacity, these resources are often underutilized for tasks beyond simple I/O delegation. This study proposes OffloadFS, a user-level file system that enables offloaded IO-intensive tasks primarily to a disaggregated storage node for near-data processing, with the option to offload to peer compute nodes as well, without the need for distributed lock management. OffloadFS optimizes cache management by reducing interference between threads performing distinct I/O operations. On top of OffloadFS, we develop OffloadDB, which enables RocksDB to offload MemTable flush and compaction operations, and OffloadPrep, which offloads image pre-processing tasks for machine learning to disaggregated storage nodes. Our evaluation shows that OffloadFS improves the performance of RocksDB and machine learning pre-processing tasks by up to 3.36x and 1.85x, respectively, compared to OCFS2.

cs.DC↗

arXiv2026

CVA: Context-aware Video-text Alignment for Video Temporal Grounding

We propose Context-aware Video-text Alignment (CVA), a novel framework to address a significant challenge in video temporal grounding: achieving temporally sensitive video-text alignment that remains robust to irrelevant background context. Our framework is built on three key components. First, we propose Query-aware Context Diversification (QCD), a new data augmentation strategy that ensures only semantically unrelated content is mixed in. It builds a video-text similarity-based pool of replacement clips to simulate diverse contexts while preventing the ``false negative" caused by query-agnostic mixing. Second, we introduce the Context-invariant Boundary Discrimination (CBD) loss, a contrastive loss that enforces semantic consistency at challenging temporal boundaries, making their representations robust to contextual shifts and hard negatives. Third, we introduce the Context-enhanced Transformer Encoder (CTE), a hierarchical architecture that combines windowed self-attention and bidirectional cross-attention with learnable queries to capture multi-scale temporal context. Through the synergy of these data-centric and architectural enhancements, CVA achieves state-of-the-art performance on major VTG benchmarks, including QVHighlights and Charades-STA. Notably, our method achieves a significant improvement of approximately 5 points in Recall@1 (R1) scores over state-of-the-art methods, highlighting its effectiveness in mitigating false negatives.

cs.LG↗

arXiv2025

Temporal Grounding as a Learning Signal for Referring Video Object Segmentation

Referring Video Object Segmentation (RVOS) aims to segment and track objects in videos based on natural language expressions, requiring precise alignment between visual content and textual queries. However, existing methods often suffer from semantic misalignment, largely due to indiscriminate frame sampling and supervision of all visible objects during training -- regardless of their actual relevance to the expression. We identify the core problem as the absence of an explicit temporal learning signal in conventional training paradigms. To address this, we introduce MeViS-M, a dataset built upon the challenging MeViS benchmark, where we manually annotate temporal spans when each object is referred to by the expression. These annotations provide a direct, semantically grounded supervision signal that was previously missing. To leverage this signal, we propose Temporally Grounded Learning (TGL), a novel learning framework that directly incorporates temporal grounding into the training process. Within this frame- work, we introduce two key strategies. First, Moment-guided Dual-path Propagation (MDP) improves both grounding and tracking by decoupling language-guided segmentation for relevant moments from language-agnostic propagation for others. Second, Object-level Selective Supervision (OSS) supervises only the objects temporally aligned with the expression in each training clip, thereby reducing semantic noise and reinforcing language-conditioned learning. Extensive experiments demonstrate that our TGL framework effectively leverages temporal signal to establish a new state-of-the-art on the challenging MeViS benchmark. We will make our code and the MeViS-M dataset publicly available.

cs.CV↗

arXiv2022

Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation

Self-supervised monocular depth estimation has been widely studied recently. Most of the work has focused on improving performance on benchmark datasets, such as KITTI, but has offered a few experiments on generalization performance. In this paper, we investigate the backbone networks (e.g. CNNs, Transformers, and CNN-Transformer hybrid models) toward the generalization of monocular depth estimation. We first evaluate state-of-the-art models on diverse public datasets, which have never been seen during the network training. Next, we investigate the effects of texture-biased and shape-biased representations using the various texture-shifted datasets that we generated. We observe that Transformers exhibit a strong shape bias and CNNs do a strong texture-bias. We also find that shape-biased models show better generalization performance for monocular depth estimation compared to texture-biased models. Based on these observations, we newly design a CNN-Transformer hybrid network with a multi-level adaptive feature fusion module, called MonoFormer. The design intuition behind MonoFormer is to increase shape bias by employing Transformers while compensating for the weak locality bias of Transformers by adaptively fusing multi-level representations. Extensive experiments show that the proposed method achieves state-of-the-art performance with various public datasets. Our method also shows the best generalization ability among the competitive methods.

cs.CV↗

arXiv2020

Channel Type Recognition in Wireless Communications: A Deep Learning Approach

In this paper, we propose two novel and practical deep-learning-based algorithms to solve the wireless channel type (WCT) recognition problem. Specifically, the WCT recognition problem is recast as a classification problem in deep learning due to their similarities, where a deep neural network (DNN) is trained off-line with a diversity of typical WCTs for fifth-generation (5G) and beyond-5G wireless communications, which is then utilized to perform online WCT determination. In the first algorithm, one WCT is regarded as a single task. While in the second scheme, one WCT is jointly characterized by several independent features, each of which is treated as a task and is classified respectively by training a DNN in a multi-task-learning manner, and the final WCT is identified by the combination of those channel features. Simulation results show that the proposed algorithms can classify various WCTs instantaneously with high accuracy, result in satisfactory block error rate and throughput, and outperform a representative baseline WCT determination scheme.

eess.SP↗

arXiv2020

Practical Scheduling Algorithms with Contiguous Resource Allocation for Next-Generation Wireless Systems

This paper proposes three novel resource and user scheduling algorithms with contiguous frequency-domain resource allocation (FDRA) for wireless communications systems. The first proposed algorithm jointly schedules users and resources selected adaptively from both ends of the bandwidth part (BWP), while the second and third ones apply disjoint user and resource selection with either single-end or dual-end BWP strategies. Distinct from existing contiguous FDRA approaches, the proposed ones comply with standards specifications for fifth-generation (5G) and beyond 5G communications, and have lower computational complexity hence are more practical. Simulation results show that all of the proposed algorithms can achieve near-optimal performance in terms of throughput and packet loss rate for low to moderate traffic load, and the first one can still perform relatively well even with a large number of users.

cs.NI↗

arXiv2020

Practical Link Adaptation Algorithm with Power Density Offsets for 5G Uplink Channels

This letter proposes a pragmatic link adaptation algorithm considering power density offsets (PDOs) for next-generation uplink wireless channels. The proposed algorithm consists of PDO calculation between a physical uplink shared channel and its associated sounding reference signal, key channel state metric generation, and modulation and coding scheme (MCS) adaptation with respect to the PDO. Scaling is applied to estimated channel matrices based on multiple reference PDO points to generate corresponding reference mutual information (MI) values, followed by interpolation or extrapolation to obtain the adapted MI and ultimately MCS. The proposed algorithm has low complexity in terms of hardware implementation, while yielding satisfactory block error rates and throughput for a wide range of PDOs as shown by simulation results.

cs.IT↗