Youngpil Jeon — accepted AI-conference papers

2026

DepthFocus: Controllable Depth Estimation for See-Through Scenes

Junhong Min, Jimin Kim, Minwook Kim, Cheol-Hui Min, Youngpil Jeon, Minyong Choi

CVPR 2026

Depth in the real world is rarely singular. Transmissive materials create layered ambiguities that confound conventional perception systems. Existing models remain passive; conventional approaches typically estimate static depth maps anchored to the nearest surface, and even recent multi-head extens

Cited by 0 Source ↗code ↗Scholar ↗

2025

S2M2: Scalable Stereo Matching Model for Reliable Depth Estimation

Junhong Min, Youngpil Jeon, Jimin Kim, Minyong Choi

ICCV 2025poster

The pursuit of a generalizable stereo matching model, capable of performing well across varying resolutions and disparity ranges without dataset-specific fine-tuning, has revealed a fundamental trade-off. Iterative local search methods achieve high scores on constrained benchmarks, but their core me…

Cited by 0 Source ↗PDF ↗Scholar ↗