Ji-Yeon Kim — accepted AI-conference papers

2024

Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation

Ji-Yeon Kim, Oh Hyun-Bin, Byung-Ki Kwon, Dahun Kim, Yongjin Kwon, Tae-Hyun Oh

RA-L 2024

We present Uni-DVPS, a unified model for Depth-aware Video Panoptic Segmentation (DVPS) that jointly tackles distinct vision tasks, i.e., video panoptic segmentation, monocular depth estimation, and object tracking. In contrast to the prior works that adopt diverged decoder networks tailored for eac

Cited by 6 Source ↗Scholar ↗

2023

Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fields

Sungheon Park, Minjung Son, Seokhwan Jang, Young Chun Ahn, Ji-Yeon Kim, Nahyup Kang

CVPR 2023highlight

Temporal interpolation often plays a crucial role to learn meaningful representations in dynamic scenes. In this paper, we propose a novel method to train spatiotemporal neural radiance fields of dynamic scenes based on temporal interpolation of feature vectors. Two feature interpolation methods are…

Cited by 59 Source ↗PDF ↗Scholar ↗