Newest papers

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

Om Shivam Verma, Shaya Farahmand, Lingjun Zhao, Lu Gan · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28530 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

La percepción colaborativa permite a los agentes recuperar la semántica de la escena y la geometría más allá del campo de visión de cualquier agente individual. Esta comprensión más amplia de la escena mejora la seguridad del transporte y mejora la eficiencia en los sistemas multi-robot. Sin embargo, los métodos de ocupación semántica colaborativa existentes se basan en anotaciones de voxel 3D densas y se limitan a reconocer objetos dentro de un conjunto predefinido de clases semánticas. Para superar estas limitaciones, presentamos CoGaussian, un marco de predicción de ocupación semántica colaborativa basado en palabras abiertas basado en Gaussian. CoGaussian representa una escena como un conjunto de modelos de base alineados con 3D Gaussians, que sirve como compactación para comunicar y representar información geométrica y sem

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 a set of foundation model-aligned sparse 3D Gaussians, which serve as a compact representation for communicating and fusing geometric and semantic information across multiple agents. On the Semantic-OPV2V benchmark, our method outperforms existing open-vocabulary single-agent approaches, highlighting the effectiveness of open-vocabulary collaborative scene understanding.

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

Topics: Computer science, Semantics (computer science), Set (abstract data type), Representation (politics), Field (mathematics), Artificial intelligence

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