16 papers
Partially Observable Zero-shot coordination by Predicting Intention of Partner
Jinnyeong Yang, Yuhwan Jeong, Hoyong Kwon +3
Zero-shot coordination in embodied settings requires acting while the partner is intermittently out of view, leaving existing methods with ambiguous partner representations and unc…
Do LLMs Act on What They Know? From Partner Representations to Cooperative Actions
Yuhwan Jeong, Jinnyeong Yang, Kuk-Jin Yoon
Cooperation with unfamiliar partners requires adapting to communication conventions that are not known in advance. We study this problem in a controlled Hanabi-derived environment…
Reuse Before You Retrieve: Diagnosing Headroom and Complementarity for Test-Time Augmentation of Embodied Multimodal Policies
Yuhwan Jeong, Kuk-Jin Yoon
Frozen vision-language-action (VLA) policies are increasingly improved at test time by sampling additional policy behaviors or introducing external demonstrations. Yet there is lit…
GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Tracking
Youngho Kim, Hoonhee Cho, Jae-Young Kang +1
Feature tracking plays a fundamental role in understanding scene motion and supports various downstream tasks. Event cameras, with their high temporal resolution and asynchronous s…
DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDAR
Hoonhee Cho, Jae-Young Kang, Yuhwan Jeong +4
In this paper, we present DSERT-RoLL, a driving dataset that incorporates stereo event, RGB, and thermal cameras together with 4D radar and dual LiDAR, collected across diverse wea…
VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting
Hoonhee Cho, Jae-Young Kang, Giwon Lee +4
End-to-end autonomous driving (E2E-AD) has emerged as a promising paradigm that unifies perception, prediction, and planning into a holistic, data-driven framework. However, achiev…
Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detection
Jae-Young Kang, Hoonhee Cho, Kuk-Jin Yoon
3D object detection is essential for autonomous systems, enabling precise localization and dimension estimation. While LiDAR and RGB cameras are widely used, their fixed frame rate…
Robust Adverse Weather Removal via Spectral-based Spatial Grouping
Yuhwan Jeong, Yunseo Yang, Youngho Yoon +1
Adverse weather conditions cause diverse and complex degradation patterns, driving the development of All-in-One (AiO) models. However, recent AiO solutions still struggle to captu…
From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras
Youngho Kim, Hoonhee Cho, Kuk-Jin Yoon
Human pose estimation is critical for applications such as rehabilitation, sports analytics, and AR/VR systems. However, rapid motion and low-light conditions often introduce motio…
Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras
Hoonhee Cho, Jae-young Kang, Youngho Kim +1
Detecting 3D objects in point clouds plays a crucial role in autonomous driving systems. Recently, advanced multi-modal methods incorporating camera information have achieved notab…
CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring
Taewoo Kim, Hoonhee Cho, Kuk-Jin Yoon
Video deblurring aims to enhance the quality of restored results in motion-blurred videos by effectively gathering information from adjacent video frames to compensate for the insu…
Towards Real-world Event-guided Low-light Video Enhancement and Deblurring
Taewoo Kim, Jaeseok Jeong, Hoonhee Cho +2
In low-light conditions, capturing videos with frame-based cameras often requires long exposure times, resulting in motion blur and reduced visibility. While frame-based motion deb…
Finding Meaning in Points: Weakly Supervised Semantic Segmentation for Event Cameras
Hoonhee Cho, Sung-Hoon Yoon, Hyeokjun Kweon +1
Event cameras excel in capturing high-contrast scenes and dynamic objects, offering a significant advantage over traditional frame-based cameras. Despite active research into lever…
Temporal Event Stereo via Joint Learning with Stereoscopic Flow
Hoonhee Cho, Jae-Young Kang, Kuk-Jin Yoon
Event cameras are dynamic vision sensors inspired by the biological retina, characterized by their high dynamic range, high temporal resolution, and low power consumption. These fe…
Towards Robust Event-based Networks for Nighttime via Unpaired Day-to-Night Event Translation
Yuhwan Jeong, Hoonhee Cho, Kuk-Jin Yoon
Event cameras with high dynamic range ensure scene capture even in low-light conditions. However, night events exhibit patterns different from those captured during the day. This d…
Quantifying Task Priority for Multi-Task Optimization
Wooseong Jeong, Kuk-Jin Yoon
The goal of multi-task learning is to learn diverse tasks within a single unified network. As each task has its own unique objective function, conflicts emerge during training, res…