Newest papers

CoGaussian: Open-Vocabulary Gaussian-based Collaborative 3D Scene Understanding

Om Shivam Verma, Shaya Farahmand, Lingjun Zhao, Lu Gan · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28530 · open-access PDF

French

La perception collaborative permet aux agents de récupérer la sémantique et la géométrie de la scène au-delà du champ de vision de tout agent individuel. Cette compréhension plus large de la scène améliore la sécurité du transport et améliore l'efficacité dans les systèmes multi-robot. Toutefois, les méthodes d'occupation sémantique collaborative existantes reposent sur des annotations voxel 3D dense et sont limitées à la reconnaissance d'objets au sein d'un ensemble prédéfini de classes sémantiques. Pour surmonter ces limitations, nous présentons CoGaussian, un cadre de prévision sémantique collaborative basé sur le vocabulaire ouvert de Gaussian.

Machine translation (Meta M2M100); the English original follows.

Abstract

Collaborative perception enables agents to retrieve the scene semantics and geometry beyond the field of view of any individual agent. This broader scene understanding enhances transportation safety and improves efficiency in multi-robot systems. However, existing collaborative semantic occupancy methods rely on dense 3D voxel annotations and are limited to recognizing objects within a predefined set of semantic classes. To overcome these limitations, we present CoGaussian, an open-vocabulary Gaussian-based collaborative semantic occupancy prediction framework. CoGaussian represents a scene as

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28530, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange