Jinhyeok Kim — accepted AI-conference papers

2026

LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds

Jaehun Bang, Jinhyeok Kim, Minji Kim, Seungheon Jeong, Kyungdon Joo

CVPR 2026

Open-vocabulary 3D scene understanding enables users to segment novel objects in complex 3D environments through natural language. However, existing approaches remain slow, memory-intensive, and overly complex due to iterative optimization and dense per-Gaussian feature assignments. To address this,

Cited by 0 Source ↗code ↗Scholar ↗

2024

Fracture Assembly with Segmentation And Iterative Registration

Jinhyeok Kim, Inha Lee, Kyungdon Joo

ICASSP 2024accepted

Reassembling broken fractures back to their original shape remains a complex challenge. While prior research has demonstrated impressive results in domain-specific assembly, these methods largely depend on human-designed structural priors or struggle with assembling diverse shapes. To tackle this is…

Cited by 0 Source ↗Scholar ↗