arXiv subjects

Seungyeop Kang

Publications and source records attributed to Seungyeop Kang.

4 recordsLinked to original sources

arXiv2026

MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction

Establishing consistent correspondences across images is essential for 3D vision tasks such as structure-from-motion (SfM), yet most existing matchers operate in a pairwise manner, often producing fragmented and geometrically inconsistent tracks when their predictions are chained across views. We propose MV-RoMa, a multi-view dense matching model that jointly estimates dense correspondences from a source image to multiple co-visible targets. Specifically, we design an efficient model architecture which avoids high computational cost of full cross-attention for multi-view feature interaction: (i) multi-view encoder that leverages pair-wise matching results as a geometric prior, and (ii) multi-view matching refiner that refines correspondences using pixel-wise attention. Additionally, we propose a post-processing strategy that integrates our model's consistent multi-view correspondences as high-quality tracks for SfM. Across diverse and challenging benchmarks, MV-RoMa produces more reliable correspondences and substantially denser, more accurate 3D reconstructions than existing sparse and dense matching methods. Project page: https://icetea-cv.github.io/mv-roma/.

cs.CV↗

arXiv2023

NIPQ: Noise proxy-based Integrated Pseudo-Quantization

Straight-through estimator (STE), which enables the gradient flow over the non-differentiable function via approximation, has been favored in studies related to quantization-aware training (QAT). However, STE incurs unstable convergence during QAT, resulting in notable quality degradation in low precision. Recently, pseudoquantization training has been proposed as an alternative approach to updating the learnable parameters using the pseudo-quantization noise instead of STE. In this study, we propose a novel noise proxy-based integrated pseudoquantization (NIPQ) that enables unified support of pseudoquantization for both activation and weight by integrating the idea of truncation on the pseudo-quantization framework. NIPQ updates all of the quantization parameters (e.g., bit-width and truncation boundary) as well as the network parameters via gradient descent without STE instability. According to our extensive experiments, NIPQ outperforms existing quantization algorithms in various vision and language applications by a large margin.

cs.LG↗

arXiv2022

Theoretical and Practical Bounds on the Initial Value of Skew-Compensated Clock for Clock Skew Compensation Algorithm Immune to Floating-Point Precision Loss

A clock skew compensation algorithm was recently proposed based on the extension of Bresenham's line drawing algorithm (Kim and Kang, IEEE Commun. Lett., vol. 26, no. 4, pp. 902--906, Apr. 2022), which takes into account the discrete nature of clocks in digital communication systems and mitigates the effect of limited floating-point precision on clock skew compensation. It lacks, however, a theoretical analysis of the range of the initial value of skew-compensated clock, which is also an initial condition for the proposed algorithm. In this letter, we provide practical as well as theoretical bounds on the initial value of skew-compensated clock based on a systematic analysis of the errors of floating-point operations, which replace the approximate bounds in Theorem 1 of the prior work.

cs.NI↗

arXiv2021

Clock Skew Compensation Algorithm Immune to Floating-Point Precision Loss

We propose a novel clock skew compensation algorithm based on Bresenham's line drawing algorithm. The proposed algorithm can avoid the effect of limited floating-point precision (e.g., 32-bit single precision) on clock skew compensation and thereby provide high-precision time synchronization even with resource-constrained sensor nodes in wireless sensor networks.

cs.NI↗