3 papers
cs.CV2025
Training-Free Global Geometric Association for 4D LiDAR Panoptic Segmentation
Gyeongrok Oh, Youngdong Jang, Jonghyun Choi +3
Dominant paradigms for 4D LiDAR panoptic segmentation are usually required to train deep neural networks with large superimposed point clouds or design dedicated modules for instan…
cs.RO2025
Active Test-time Vision-Language Navigation
Heeju Ko, Sungjune Kim, Gyeongrok Oh +5
Vision-Language Navigation (VLN) policies trained on offline datasets often exhibit degraded task performance when deployed in unfamiliar navigation environments at test time, wher…
cs.CV2025
3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation
Gyeongrok Oh, Sungjune Kim, Heeju Ko +7
The resolution of voxel queries significantly influences the quality of view transformation in camera-based 3D occupancy prediction. However, computational constraints and the prac…