7 papers
AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models
Hyeongjun Heo, Seungyeon Woo, Sang Min Kim +4
Despite remarkable progress in Vision-Language-Action models (VLAs) for robot manipulation, these large pre-trained models require fine-tuning to be deployed in specific environmen…
Finding 3D Scene Analogies with Multimodal Foundation Models
Junho Kim, Young Min Kim
Connecting current observations with prior experiences helps robots adapt and plan in new, unseen 3D environments. Recently, 3D scene analogies have been proposed to connect two 3D…
LTGS: Long-Term Gaussian Scene Chronology From Sparse View Updates
Minkwan Kim, Seungmin Lee, Junho Kim +1
Recent advances in novel-view synthesis can create the photo-realistic visualization of real-world environments from conventional camera captures. However, the everyday environment…
Point2Act: Efficient 3D Distillation of Multimodal LLMs for Zero-Shot Context-Aware Grasping
Sang Min Kim, Hyeongjun Heo, Junho Kim +2
We propose Point2Act, which directly retrieves the 3D action point relevant to a contextually described task, leveraging Multimodal Large Language Models (MLLMs). Foundation models…
Learning 3D Scene Analogies with Neural Contextual Scene Maps
Junho Kim, Gwangtak Bae, Eun Sun Lee +1
Understanding scene contexts is crucial for machines to perform tasks and adapt prior knowledge in unseen or noisy 3D environments. As data-driven learning is intractable to compre…
Fully Geometric Panoramic Localization
Junho Kim, Jiwon Jeong, Young Min Kim
We introduce a lightweight and accurate localization method that only utilizes the geometry of 2D-3D lines. Given a pre-captured 3D map, our approach localizes a panorama image, ta…
Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistency
Eun Sun Lee, Junho Kim, Young Min Kim
We propose a light-weight, self-supervised adaptation for a visual navigation agent to generalize to unseen environment. Given an embodied agent trained in a noiseless environment,…