Metraipolis › archive › dc_af54861a2f58
HIGS: Hierarchical Implicit Grids for Joint Geometric and Semantic Scene Understanding — arXiv:2609.38620
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38620
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:45:25.899Z
- SHA-256 of the archived text
a390c7f91161ec80dda05059d26a00bbb12dedc2aa66fbec5783aaa501be2ed6- Stable URL of this page
https://metraipolis.com/documento/dc_af54861a2f58
How to cite
HIGS: Hierarchical Implicit Grids for Joint Geometric and Semantic Scene Understanding — arXiv:2609.38620 — arXiv (en), https://arxiv.org/abs/2609.38620 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af54861a2f58 (Metraipolis archive dc_af54861a2f58, sha256 a390c7f91161ec80dda05059d26a00bbb12dedc2aa66fbec5783aaa501be2ed6)
BibTeX
@misc{dcaf54861a2f58,
title = {HIGS: Hierarchical Implicit Grids for Joint Geometric and Semantic Scene Understanding — arXiv:2609.38620},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38620},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af54861a2f58; sha256 a390c7f91161ec80dda05059d26a00bbb12dedc2aa66fbec5783aaa501be2ed6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38620. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural implicit representations have had a significant impact on scene reconstruction by enabling robots to build continuous, differentiable, and high-fidelity 3D maps. Most existing works focus on geometric reconstruction and lack semantic information for high-level spatial understanding and task planning. Also, as the scale and complexity of the environment increase, neural representations face the challenge of maintaining computational efficiency in back-end optimization. To resolve these two challenges, we introduce a hierarchical neural field that leverages multiresolution submaps to achieve an efficient and scalable implicit representation, and a unified query and decoding mechanism to support both geometric and semantic features. More specifically, the learnable map features can be converted to the output with the query and decoding process for both training and inference. For large-scale representation, we decompose a scene into overlapping submaps and do hierarchical optimization within each local submap, thus enabling scalable computation. To further improve efficiency, we design feature encoders that predict initial hierarchical grid features to substantially reduce the time needed to optimize the submap features from scratch. To correct estimation drift among submaps, we align and fuse them entirely within the implicit feature space, leading to substantial acceleration by avoiding the need to decode the final output. Building upon this efficient hierarchical representation, we embed both geometric features and vision-language latent features into the map, and demonstrate it on both Signed Distance Field (SDF) construction and open-vocabulary object grounding. Our approach significantly improves computation and memory efficiency, maintains high estimation accuracy, and endows the robot with spatial awareness on large-scale real-world benchmarks. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.38620 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T14:19:00.589Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).