arXiv subjects

Minseong Kim

Publications and source records attributed to Minseong Kim.

10 recordsLinked to original sources

arXiv2026

Variable-Horizon Workforce Demand Forecasting with an Aggregate Demand Constraint for Construction Workforce Planning

Workforce planning is a recurring operational decision during construction projects that requires accurate forecasts of the future workforce demand for individual tasks. However, in practice, tasks have different completion dates, resulting in variable forecast horizons. In addition, the sum of the predicted daily workforce demands must equal the total workforce allocation specified in advance. Most existing machine-learning (ML)-based forecasting models assume fixed-length outputs and do not explicitly impose an aggregate demand constraint, making them unsuitable for these operational requirements. To address this problem, this study proposes constraint-preserving residual allocation forecasting (CP-RAF). The CP-RAF represents an observed workforce demand time series as a coefficient vector and retrieves completed tasks with similar temporal shapes. Then, it estimates the allocation profile over the remaining task duration using similarity-weight averaging. The predefined remaining workforce demand for each task was distributed according to the estimated profile, and the forecast horizon was adjusted while retaining profile characteristics. This procedure accommodates variable forecast horizons while preserving the aggregate demand constraints. CP-RAF was evaluated using workforce demand field data. The results showed that CP-RAF outperformed eight baseline models in medium- and long-horizon fixed-length forecasting and maintained low forecast errors under variable-length forecasting. By directly incorporating operational constraints into the forecasting procedure, the proposed method provides a framework suitable for workforce allocation in construction practices.

cs.CE↗

arXiv2026

GuideCAD: A Lightweight Multimodal Framework for 3D CAD Model Generation via Prefix Embedding

Multi-modal approaches used for 3D CAD generation require substantial computational resources, necessitating efficient training. To address this, we propose GuideCAD, which leverages semantically rich visual-textual representations having only a small number of trainable parameters to generate 3D CAD models. Specifically, GuideCAD uses a mapping network that converts image embeddings into prefix embeddings, enabling a pretrained large language model to integrate visual and textual information. As a result, a transformer-based decoder predicts the construction sequence using the visual-textual embeddings in order to generate the 3D CAD model. For experimental evaluation, we construct a new dataset, referred to as GuideCAD, which consists of text-image pairs. Each pair includes a text prompt that represents a 3D CAD construction sequence and its corresponding 3D CAD image. Our experimental results show that GuideCAD generates comparably high-quality 3D CAD models while using approximately four times fewer parameters and achieving twice the training efficiency compared to fine-tuning approaches. We have released the source code and dataset for our method at: https://github.com/mskimS2/GuideCAD

cs.CV↗

arXiv2026

PAColorHolo: A Perceptually-Aware Color Management Framework for Holographic Displays

Holographic displays offer significant potential for augmented and virtual reality applications by reconstructing wavefronts that enable continuous depth cues and natural parallax without vergence-accommodation conflict. However, despite advances in pixel-level image quality, current systems struggle to achieve perceptually accurate color reproduction--an essential component of visual realism. These challenges arise from complex system-level distortions caused by coherent laser illumination, spatial light modulator imperfections, chromatic aberrations, and camera-induced color biases. In this work, we propose a perceptually-aware color management framework for holographic displays that jointly addresses input-output color inconsistencies through color space transformation, adaptive illumination control, and neural network-based perceptual modeling of the camera's color response. We validate the effectiveness of our approach through numerical simulations, optical experiments, and a controlled user study. The results demonstrate substantial improvements in perceptual color fidelity, laying the groundwork for perceptually driven holographic rendering in future systems.

cs.GR↗

arXiv2025

DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting

We present a Directional Consistency (DC)-driven Adaptive Density Control (ADC) for 3D Gaussian Splatting (DC4GS). Whereas the conventional ADC bases its primitive splitting on the magnitudes of positional gradients, we further incorporate the DC of the gradients into ADC, and realize it through the angular coherence of the gradients. Our DC better captures local structural complexities in ADC, avoiding redundant splitting. When splitting is required, we again utilize the DC to define optimal split positions so that sub-primitives best align with the local structures than the conventional random placement. As a consequence, our DC4GS greatly reduces the number of primitives (up to 30% in our experiments) than the existing ADC, and also enhances reconstruction fidelity greatly.

cs.CV↗

arXiv2024

ContrastCAD: Contrastive Learning-based Representation Learning for Computer-Aided Design Models

The success of Transformer-based models has encouraged many researchers to learn CAD models using sequence-based approaches. However, learning CAD models is still a challenge, because they can be represented as complex shapes with long construction sequences. Furthermore, the same CAD model can be expressed using different CAD construction sequences. We propose a novel contrastive learning-based approach, named ContrastCAD, that effectively captures semantic information within the construction sequences of the CAD model. ContrastCAD generates augmented views using dropout techniques without altering the shape of the CAD model. We also propose a new CAD data augmentation method, called a Random Replace and Extrude (RRE) method, to enhance the learning performance of the model when training an imbalanced training CAD dataset. Experimental results show that the proposed RRE augmentation method significantly enhances the learning performance of Transformer-based autoencoders, even for complex CAD models having very long construction sequences. The proposed ContrastCAD model is shown to be robust to permutation changes of construction sequences and performs better representation learning by generating representation spaces where similar CAD models are more closely clustered. Our codes are available at https://github.com/cm8908/ContrastCAD.

cs.CV↗

arXiv2021

Brick partition problems in three dimensions

A $d$-dimensional brick is a set $I_1\times \cdots \times I_d$ where each $I_i$ is an interval. Given a brick $B$, a brick partition of $B$ is a partition of $B$ into bricks. A brick partition $\mathcal{P}_d$ of a $d$-dimensional brick is $k$-piercing if every axis-parallel line intersects at least $k$ bricks in $\mathcal{P}_d$. Bucic et al. explicitly asked the minimum size $p(d, k)$ of a $k$-piercing brick partition of a $d$-dimensional brick. The answer is known to be $4(k-1)$ when $d=2$. Our first result almost determines $p(3, k)$. Namely, we construct a $k$-piercing brick partition of a $3$-dimensional brick with $12k-15$ parts, which is off by only $1$ from the known lower bound. As a generalization of the above question, we also seek the minimum size $s(d, k)$ of a brick partition $\mathcal{P}_d$ of a $d$-dimensional brick where each axis-parallel plane intersects at least $k$ bricks in $\mathcal{P}_d$. We resolve the question in the $3$-dimensional case by determining $s(3, k)$ for all $k$.

math.CO↗

arXiv2020

Time-consistent decisions and rational expectation equilibrium existence in DSGE models

Under some initial conditions, it is shown that time consistency requirements prevent rational expectation equilibrium (REE) existence for dynamic stochastic general equilibrium models induced by consumer heterogeneity, in contrast to static models. However, one can consider REE-prohibiting initial conditions as limits of other initial conditions. The REE existence issue then is overcome by using a limit of economies. This shows that significant care must be taken of when dealing with rational expectation equilibria.

econ.TH↗

arXiv2018

Unbiased Image Style Transfer

Recent fast image style transferring methods use feed-forward neural networks to generate an output image of desired style strength from the input pair of a content and a target style image. In the existing methods, the image of intermediate style between the content and the target style is obtained by decoding a linearly interpolated feature in encoded feature space. However, there has been no work on analyzing the effectiveness of this kind of style strength interpolation so far. In this paper, we tackle the missing work on the in-depth analysis of style interpolation and propose a method that is more effective in controlling style strength. We interpret the training task of a style transfer network as a regression learning between the control parameter and output style strength. In this understanding, the existing methods are biased due to the fact that training is performed with one-sided data of full style strength (alpha = 1.0). Thus, this biased learning does not guarantee the generation of a desired intermediate style corresponding to the style control parameter between 0.0 and 1.0. To solve this problem of the biased network, we propose an unbiased learning technique which uses unbiased training data and corresponding unbiased loss for alpha = 0.0 to make the feed-forward networks to generate a zero-style image, i.e., content image when alpha = 0.0. Our experimental results verified that our unbiased learning method achieved the reconstruction of a content image with zero style strength, better regression specification between style control parameter and output style, and more stable style transfer that is insensitive to the weight of style loss without additive complexity in image generating process.

cs.CV↗

arXiv2018

Uncorrelated Feature Encoding for Faster Image Style Transfer

Recent fast style transfer methods use a pre-trained convolutional neural network as a feature encoder and a perceptual loss network. Although the pre-trained network is used to generate responses of receptive fields effective for representing style and content of image, it is not optimized for image style transfer but rather for image classification. Furthermore, it also requires a time-consuming and correlation-considering feature alignment process for image style transfer because of its inter-channel correlation. In this paper, we propose an end-to-end learning method which optimizes an encoder/decoder network for the purpose of style transfer as well as relieves the feature alignment complexity from considering inter-channel correlation. We used uncorrelation loss, i.e., the total correlation coefficient between the responses of different encoder channels, with style and content losses for training style transfer network. This makes the encoder network to be trained to generate inter-channel uncorrelated features and to be optimized for the task of image style transfer which maintained the quality of image style only with a light-weighted and correlation-unaware feature alignment process. Moreover, our method drastically reduced redundant channels of the encoded feature and this resulted in the efficient size of structure of network and faster forward processing speed. Our method can also be applied to cascade network scheme for multiple scaled style transferring and allows user-control of style strength by using a content-style trade-off parameter.

cs.CV↗

arXiv2016

Inconsistency of the Zermelo-Fraenkel set theory with the axiom of choice and its effects on the computational complexity

This paper exposes a contradiction in the Zermelo-Fraenkel set theory with the axiom of choice (ZFC). While Godel's incompleteness theorems state that a consistent system cannot prove its consistency, they do not eliminate proofs using a stronger system or methods that are outside the scope of the system. The paper shows that the cardinalities of infinite sets are uncontrollable and contradictory. The paper then states that Peano arithmetic, or first-order arithmetic, is inconsistent if all of the axioms and axiom schema assumed in the ZFC system are taken as being true, showing that ZFC is inconsistent. The paper then exposes some consequences that are in the scope of the computational complexity theory.

cs.LO↗