3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning

Yuncong Yang; Han Yang; Jiachen Zhou; Peihao Chen; Hongxin Zhang; Yilun Du; Chuang Gan

doi:10.1109/cvpr52734.2025.01612

CVPR2025顶会

3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning

Yuncong Yang, Han Yang, Jiachen Zhou, Peihao Chen, Hongxin Zhang, Yilun Du, Chuang Gan

arXiv DOI 出版方

2025年份

17顶会引用

摘要

Figure 1. With 3D-Mem, explored regions are represented by a set of Memory Snapshots capturing clusters of co-visible objects, i.e., the objects observable in a single image observation, along with their spatial relationships and background context, as shown in the bottom-left example. Unexplored regions are represented by navigable frontiers along with image observations, referred to as Frontier Snapshots.