arXiv Computer Vision October 8, 2026 By Liyan Chen, Hairong Yin, Huangying Zhan, Yi Xu, Raymond A. Yeh, Philippos Mordohai

ActiveLang: Active Open-Vocabulary 3D Mapping with Semantic-Uncertainty-Guided Exploration

Read the original on arXiv Computer Vision →

ActiveLang is an autonomous system that builds language‑annotated 3D maps by actively exploring environments. It uses a compact dual‑Gaussian representation to jointly reconstruct geometry, appearance, and open‑vocabulary semantics while adapting language features online. The planner selects informative viewpoints, reducing the number of observations and computational cost, and experiments on Replica and ScanNet++ show significant gains in 2D and 3D open‑vocabulary segmentation compared to existing baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

2d ago

OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception

arXiv:2610.07569v1 Announce Type: cross Abstract: Dense 3D mapping with semantic understanding is essential for robotic perception in complex environments. Recent 3D Gaussian Splatting-based mapping...

By Binh Long Nguyen, Kien Nguyen, Clinton Fookes, Peyman Moghadam

robotics benchmarks

arXiv AI

Jun 8

SCOUT: Semantic scene COverage via Uncertainty-guided Traversal

arXiv:2606. 06721v1 Announce Type: cross Abstract: Robots that operate over extended periods should not merely visit space; they should progressively understand it.

By Junyu Mao, Sara Ayoubi, Vishnu D. Sharma, Ilija Had\v{z}i\'c, Matthew Andrews

agents robotics

arXiv AI

Aug 11

RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation

arXiv:2601. 10168v3 Announce Type: replace-cross Abstract: Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet current 3DSG construction methods suffer from semantic inconsistencies caused by noisy cross-image aggregation under occlusions and constrained viewpoints.

By Yue Chang, Rufeng Chen, Zhaofan Zhang, Yi Chen, Yifan Tian, Sihong Xie

llms rag robotics multimodal benchmarks

arXiv Computer Vision

Sep 21

A Scene Language Model for Open-Vocabulary Scene Mapping

The paper introduces SceneLM, a vision‑language model that maintains an open‑vocabulary 3D scene map using only a structured text list of objects as persistent memory. The model updates this textual map by adding, editing, and removing objects for each input image, learning the process through supervision tasks and an automatic annotation pipeline. Evaluations on language‑grounded retrieval and localization benchmarks show competitive performance with traditional mapping systems while producing a 6‑12× more compact representation, and the model can run online on an edge device such as a quadruped robot.

By Adam Lilja, Fabio H\"ubel, Siming He, Junsheng Fu, Claire Tomlin, Lars Hammarstrand, Jitendra Malik, Jonas Frey, Marco Pavone

llms rag multimodal benchmarks

arXiv Computer Vision

Sep 23

VEOcc: Voxel-Centric Online Semantic Occupancy Prediction For Embodied Scene Understanding

arXiv:2605.25059v4 Announce Type: replace Abstract: Crucial for autonomous exploration, online 3D occupancy prediction and mapping incrementally construct dense spatial representations on the fly. Em...

By Ruoyu Wang, Yong Liu, Jiahan Li, Sheng Tao, Yuhang Lin, Yukai Ma

agents robotics benchmarks

arXiv AI

Aug 3

AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance

arXiv:2512. 05131v2 Announce Type: replace-cross Abstract: Active 3D reconstruction enables an agent to autonomously select viewpoints to efficiently obtain accurate and complete scene geometry, rather than passively reconstructing scenes from pre-collected images.

By Tianling Xu, Shengzhe Gan, Leslie Gu, Yuelei Li, Fangneng Zhan, Hanspeter Pfister

llms agents multimodal benchmarks

One email a morning, machine-written

Related stories

OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception

SCOUT: Semantic scene COverage via Uncertainty-guided Traversal

RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation

A Scene Language Model for Open-Vocabulary Scene Mapping

VEOcc: Voxel-Centric Online Semantic Occupancy Prediction For Embodied Scene Understanding

AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance