GEM-Occ: From Visual Geometry Evidence to Embodied Semantic Occupancy Memory

• URL: http://arxiv.org/abs/2607.05543v1
• Date: Mon, 06 Jul 2026 18:26:27 GMT
• Title: GEM-Occ: From Visual Geometry Evidence to Embodied Semantic Occupancy Memory
• Abstract summary: We introduce HIOcc, a hierarchical indoor occupancy benchmark that unifies ScanNet, ScanNet++, and Matterport3D.<n>We also propose GEM-Occ, a Gaussian Evidence Memory framework for semantic occupancy mapping.
• Score: 45.09153209869868
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semantic occupancy provides a structured spatial memory for embodied indoor agents by jointly representing occupied regions, observed free space, unknown areas, and object semantics. However, existing indoor occupancy benchmarks and methods mainly focus on single-view prediction or room-level online perception, leaving long-horizon semantic mapping across connected indoor spaces underexplored. We introduce HIOcc, a hierarchical indoor occupancy benchmark that unifies ScanNet, ScanNet++, and Matterport3D under a common sparse semantic occupancy format while preserving their native observation geometries, including perspective RGB-D frames and pano-centric observation groups. HIOcc supports three complementary evaluation regimes: local semantic occupancy prediction, room-level online occupancy mapping, and building-level mapping across connected panoramic environments. We further propose GEM-Occ, a Gaussian Evidence Memory framework for semantic occupancy mapping. Rather than using pointmaps as persistent map states, GEM-Occ treats local visual geometry predictions as transient evidence, converts them into semantic Gaussian occupancy evidence and free-space ray evidence, and fuses them into a persistent hierarchical memory through visibility- and uncertainty-aware causal updates. The memory is organized into local caches, room-level submaps, and a building-level graph, and can be queried at any time through Gaussian-to-occupancy splatting. Experiments on HIOcc show that GEM-Occ improves local occupancy prediction, online map stability, free-space reasoning, revisit consistency, and building-level scalability over prior indoor occupancy and Gaussian-based mapping baselines.

Related papers

• GPOcc++: Unified Sparse Gaussian Occupancy Prediction with Visual Geometry Priors [70.03915250336668]
  We introduce GPOcc, which transforms visual geometry priors into occupancy-aware sparse Gaussian representations.<n>Building on GPOcc, GPOcc++ models multi-view observations and temporal sequences within a unified framework.<n>Experiments on both indoor and outdoor benchmarks demonstrate consistently strong performance across both multi-view and temporal settings.
  arXiv  Detail & Related papers  (2026-07-15T06:21:25Z)
• G$^2$TAM: Geometry Grounded Track Anything Model [49.05553245076823]
  We propose a unified framework for promptable instance tracking in 3D using only unordered RGB images or videos.<n>G$2$TAM employs spatially aligned geometric representations as implicit memory, ensuring stable instance identity and localization across frames and views.<n>At its core is a cross-modal spatial encoder that integrates visual and textual prompts into a shared geometric space, enabling end-to-end spatial reconstruction and instance-consistent mask prediction.
  arXiv  Detail & Related papers  (2026-07-04T09:32:13Z)
• S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence [77.5121349100339]
  textscS-Agent reshapes spatial perception into scene-centric understanding beyond frame-centric recognition.<n>textscS-Agent casts the VLM as a semantic planner that decides what evidence is needed.<n>textscS-Agent consistently improves both open-source and closed-source VLMs in a training-free manner.
  arXiv  Detail & Related papers  (2026-06-18T17:34:55Z)
• GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning [9.203056739430865]
  GSMem is a zero-shot embodied exploration and reasoning framework built upon 3D Gaussian Splatting (3DGS)<n>By explicitly parameterizing continuous geometry and dense appearance, 3DGS serves as a persistent spatial memory that endows the agent with textitSpatial Recollection<n>We introduce a hybrid exploration strategy that combines VLM-driven semantic scoring with a 3DGS-based coverage objective, balancing task-aware exploration with geometric coverage.
  arXiv  Detail & Related papers  (2026-03-19T16:55:54Z)
• Seeing Where to Deploy: Metric RGB-Based Traversability Analysis for Aerial-to-Ground Hidden Space Inspection [48.120690574682875]
  We present a metric RGB-based geometric-semantic reconstruction and traversability analysis framework for aerial-to-ground hidden space inspection.<n>Experiments on a tethered UAV-UGV platform demonstrate reliable deployment-zone identification in hidden space scenarios.
  arXiv  Detail & Related papers  (2026-03-15T22:20:59Z)
• Thinking on Maps: How Foundation Model Agents Explore, Remember, and Reason Map Environments [10.485672302572368]
  Map environments provide a fundamental medium for representing spatial structure. Understanding how foundation model (FM) agents understand and act in such environments is critical for enabling reliable map-based reasoning and applications.<n>We propose an interactive evaluation framework to analyze how FM agents explore, remember, and reason in symbolic map environments.
  arXiv  Detail & Related papers  (2025-12-30T23:04:29Z)
• Semantic Zone based 3D Map Management for Mobile Robot [0.552480439325792]
  3D maps consume substantial memory, making it difficult to maintain complete map data within limited computational resources.<n>Existing SLAM frameworks typically rely on geometric distance or temporal metrics for memory management.<n>We propose a semantic zone-based 3D map management method that shifts the paradigm from geometry-centric to semantics-centric control.
  arXiv  Detail & Related papers  (2025-12-13T07:55:40Z)
• MapBERT: Bitwise Masked Modeling for Real-Time Semantic Mapping Generation [15.116320098263149]
  MapBERT is a novel framework designed to model the distribution of unseen spaces.<n>We show that MapBERT achieves state-of-the-art semantic map generation.<n> Experiments on Gibson benchmarks show that MapBERT achieves state-of-the-art semantic map generation.
  arXiv  Detail & Related papers  (2025-06-09T01:55:55Z)
• GridMM: Grid Memory Map for Vision-and-Language Navigation [40.815400962166535]
  Vision-and-language navigation (VLN) enables the agent to navigate to a remote location following the natural language instruction in 3D environments. We build the top-down egocentric and dynamically growing Grid Memory Map to structure the visited environment. From a global perspective, historical observations are projected into a unified grid map in a top-down view, which can better represent the spatial relations of the environment.
  arXiv  Detail & Related papers  (2023-07-24T16:02:42Z)
• Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building [29.630483662400444]
  We propose and apply the concept of Fragmentation-and-Recall (FARMap) in the mapping of large spaces. Agents solve the mapping problem by building local maps via a surprisal-based clustering of space. We demonstrate that FARMap replicates the fragmentation points observed in animal studies.
  arXiv  Detail & Related papers  (2023-07-11T20:40:19Z)
• OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception [73.05425657479704]
  We propose OpenOccupancy, which is the first surrounding semantic occupancy perception benchmark. We extend the large-scale nuScenes dataset with dense semantic occupancy annotations. Considering the complexity of surrounding occupancy perception, we propose the Cascade Occupancy Network (CONet) to refine the coarse prediction.
  arXiv  Detail & Related papers  (2023-03-07T15:43:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.