2 papers
cs.CV2026
MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction
Jongmin Lee, Seungyeop Kang, Sungjoo Yoo
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,…
cs.LG2022
NIPQ: Noise proxy-based Integrated Pseudo-Quantization
Juncheol Shin, Junhyuk So, Sein Park +3
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…