Seungyeop Kang — accepted AI-conference papers

2026

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

Jongmin Lee, Seungyeop Kang, Sungjoo Yoo

CVPR 2026

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 pr

Cited by 0 Source ↗Scholar ↗

2023

NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization

Juncheol Shin, Junhyuk So, Sein Park, Seungyeop Kang, Sungjoo Yoo, Eunhyeok Park

CVPR 2023poster

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-pre…

Cited by 28 Source ↗PDF ↗code ↗Scholar ↗