Reproduce “OREN-X: Octree Residual Network for Real-Time Multi-Modal Mapping” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zhirui Dai, Qihao Qian, Dinh Minh Nguyen, Quan-Dung Pham, Kiana Bronder, Carlos Nieto-Granda, Yiyu Chen, Quan Nguyen and 1 more
OREN-X combines geometry, appearance, occupancy, and vision-language features in a shared octree map with shared indexing and joint training. It uses cross-modal supervision to update the modalities. On Replica’s eight-scene mean, its near-surface SDF MAE is 1.14 cm, down from OREN’s 1.70 cm, a reported 33% reduction. nvblox has better mesh metrics; this is benchmark evidence, not downstream navigation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.