activity
20242026
collaborators

8 papers

cs.CV2026

Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens

Rit Gangopadhyay, Jung-Hee Kim, Xien Chen +3

We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images. Despite being trained on tens of millions of images…

cs.CV2026

Radar-Guided Polynomial Fitting for Metric Depth Estimation

Patrick Rim, Hyoungseob Park, Vadim Ezhov +2

We propose POLAR, a novel radar-guided depth estimation method that introduces polynomial fitting to efficiently transform scaleless depth predictions from pretrained monocular dep…

cs.CV2026

TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception

Runjian Chen, Hyoungseob Park, Bo Zhang +3

Labeling LiDAR point clouds is notoriously time-and-energy-consuming, which spurs recent unsupervised 3D representation learning methods to alleviate the labeling burden in LiDAR p…

cs.CV2025

ETA: Energy-based Test-time Adaptation for Depth Completion

Younjoon Chung, Hyoungseob Park, Patrick Rim +7

We propose a method for test-time adaptation of pretrained depth completion models. Depth completion models, trained on some ``source'' data, often predict erroneous outputs when t…

cs.CV2025

UnCLe: Benchmarking Unsupervised Continual Learning for Depth Completion

Xien Chen, Rit Gangopadhyay, Michael Chu +3

We propose UnCLe, the first standardized benchmark for Unsupervised Continual Learning of a multimodal 3D reconstruction task: Depth completion aims to infer a dense depth map from…

cs.CV2025

Progressive Test Time Energy Adaptation for Medical Image Segmentation

Xiaoran Zhang, Byung-Woo Hong, Hyoungseob Park +5

We propose a model-agnostic, progressive test-time energy adaptation approach for medical image segmentation. Maintaining model performance across diverse medical datasets is chall…