Wongyeom Kim

Wongyeom Kim

Auto-generated profile, based on publicly available information

Wongyeom Kim

Department of Computer Science and Artificial Intelligence, Dongguk University, Jung-gu, Seoul, Republic of Korea

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 January 2025 in IEEE Access
Verified
Journal Article
Open access
SLSeongbeen Lee
Seongbeen Lee
GLGyuhyuk Lee
Gyuhyuk Lee
WKWongyeom Kim
Wongyeom Kim
JKJunoh Kim
Junoh Kim
JPJisun Park
Jisun Park
KCKyungeun Cho
Kyungeun Cho
In 3 vs. 3 online basketball games, finite state machine (FSM)-based Game artificial intelligence (AI) has traditionally been employed. However, limitations such as repetitive behavior patterns and challenges in maintaining systems during redesigns have led to increased research into reinforcement learning-based AI. This shift aims to address the shortcomings of FSM-based approaches. Nevertheless, applying multi-agent reinforcement learning-based AI in commercial online basketball games presents significant challenges, particularly in ensuring real-time processing, which requires efficient methods for managing observational data. In addition, the stochastic nature of action selection in reinforcement learning complicates the accurate learning of behaviors through explicit decision data. Moreover, reinforcement learning, which self-optimizes through exploration and develops its own rules, struggles to mimic human-like behavior patterns that follow predefined strategies in Sports Game. This study introduces a human strategy-based reinforcement learning method designed to address these challenges and replicate human gameplay that adheres to human-defined strategies. The learning of human strategies is enhanced using Ray for the real-time processing of observational data and a multi-phase reward system that distinctly defines rewards based on specific objectives. Furthermore, the proposed method enables real-time, strategy-based action guidance through a Human Strategy AI trained on human-defined strategies. Experimental results demonstrate that in a stochastic basketball game environment, this approach enabled the determination of precise actions and achieved human-like gameplay through the Human Strategy AI.

24 February 2025 in IEEE Access
Verified
Journal Article
Open access
WKWongyeom Kim
Wongyeom Kim
JPJisun Park
Jisun Park
KCKyungeun Cho
Kyungeun Cho
Neural implicit surface reconstruction has recently emerged as a prominent paradigm in multi-view 3D reconstruction using deep learning. In contrast to traditional multi-view stereo methods, signed distance function (SDF)-based approaches leverage neural networks to effectively represent 3D scenes. Furthermore, to reconstruct scenes and individual objects separately, some studies have extended the framework for object-compositional neural implicit surface reconstruction by utilizing 2D instance masks to supervise the SDF of each object. Nonetheless, these methods often reconstruct objects as partial shapes in scenes captured from sparse viewpoints or in complex scenes containing multiple objects. This issue primarily stems from the absence of a 3D prior, which fails to provide sufficient geometry for partially observed and occluded regions. We propose a framework for completing the partial object shapes of object-compositional neural implicit representation utilizing a diffusion-based 3D mesh generation model. The existing diffusion model, trained only on large-scale 3D object datasets, generates complete shapes from partial shapes; however, their results differ significantly from the objects in the scene. To complete the representation of partial shapes while ensuring shape consistency across multi-view images, we combine the SDF values, output by the diffusion model, with the object-compositional neural implicit representation. The combined representation is then volume-rendered to fine-tune the diffusion model utilizing a 2D prior. Furthermore, the complete shape generated by our method can serve as pseudo 3D priors to provide the geometry for the unobserved regions in object-compositional representation. Extensive experiments demonstrate that our novel framework significantly improves the reconstruction quality of unobserved regions.

6 August 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
KWKim Wongyeom
Kim Wongyeom
KCKyungeun Cho
Kyungeun Cho
Encoding 3D indoor scenes using object-compositional neural implicit representations is promising for various applications, but accurately reconstructing regions that are unobserved or occluded in the input images remains challenging. Recent approaches aim to address missing information in these regions by combining object-level understanding with additional guidance signals. In this paper, we propose VGO-Recon, which incorporates visual question answering (VQA)-based guidance signals into the reconstruction optimization to improve the geometry and appearance of individual objects in novel views. The core component of our method is an alignment score loss computed using a pretrained VQA model, which encourages alignment between volume-rendered images from the neural representation and textual descriptions. Furthermore, we introduce a volume rendering strategy that leverages interpolated geometry and appearance from a predicted object-centric value grid to reduce memory overhead. Extensive experiments on both synthetic and real-world datasets demonstrate that our method improves geometric and appearance quality, maintains multi-view consistency across input images, and supports text-driven editing.