Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors

• URL: http://arxiv.org/abs/2606.06891v1
• Date: Fri, 05 Jun 2026 04:16:24 GMT
• Title: Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors
• Abstract summary: We present an online 3D vision-language model that enables real-time spatial understanding from streaming video.<n>Our approach adopts an autoregressive streaming control modeling based on the LLM's next-token prediction to learn when to respond.<n>To address the scarcity of streaming 3D-language data, we further develop a scalable data generation pipeline.
• Score: 54.51965288351254
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite advances in 3D scene understanding, existing 3D Large Multimodal Models operate in offline settings, requiring complete scene observations or predefined video clips. In this paper, we present an online 3D vision-language model that enables real-time spatial understanding from streaming video. Our approach adopts an autoregressive streaming control modeling based on the LLM's next-token prediction objective to learn when to respond, and employs a lightweight Visual-Spatial Feature Integration (VSFI) module to incrementally inject temporally aligned geometry priors into the visual stream. To alleviate long-context decoding overhead, we propose a plug-and-play Geometry-Adaptive Voxel Compression (GAVC) module for efficient visual token compression. To address the scarcity of streaming 3D-language data, we further develop a scalable data generation pipeline that curates over 1M online spatio-temporal 3D QA pairs and establishes a comprehensive benchmark spanning 29 tasks. Extensive experiments show that our approach significantly outperforms both proprietary and open-source models across online and offline 3D spatial understanding, reasoning, and grounding tasks. The project page is available at https://stream3d-vlm.github.io/

Related papers

• Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding [7.823301846592561]
  Stream3Dv2 is a training-free framework designed for robust streaming 3D perception.<n>We introduce a comprehensive geometric-semantic fusion mechanism that resolves geometric noise and semantic ambiguity.<n>Experiments on public datasets demonstrate that Stream3Dv2 consistently outperforms existing baselines in foundational open-vocabulary streaming 3D segmentation and detection.
  arXiv  Detail & Related papers  (2026-08-21T14:13:02Z)
• Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding [50.098085774845195]
  We propose a paradigm shift by leveraging the implicit spatial prior within large-scale generation models.<n>We introduce GeneEGA-3D (Video Extracted Generative Awareness), a plug-and-play framework that repurposes a pre-trained video diffusion model as a Latent World Simulator.
  arXiv  Detail & Related papers  (2026-03-19T17:59:58Z)
• Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy [4.1703677379815565]
  We propose Vid-LLM, a video-based 3D-MLLM that directly processes video inputs without requiring external 3D data.<n>In our method, the geometric prior are directly used to improve the performance of the sceen perception.<n>Experiments across diverse benchmarks verified the effectiveness of our method on 3D Question Answering, 3D Captioning and 3D Visual Grounding tasks.
  arXiv  Detail & Related papers  (2025-09-29T07:34:18Z)
• STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer [72.88105562624838]
  We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem.<n>By learning geometric priors from large-scale 3D datasets, STream3R generalizes well to diverse and challenging scenarios.<n>Our results underscore the potential of causal Transformer models for online 3D perception, paving the way for real-time 3D understanding in streaming environments.
  arXiv  Detail & Related papers  (2025-08-14T17:58:05Z)
• VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction [86.82819259860186]
  We introduce VLM-3R, a unified framework for Vision-Language Models (VLMs) that incorporates 3D Reconstructive instruction tuning.<n>VLM-3R processes monocular video frames by employing a geometry encoder to derive implicit 3D tokens that represent spatial understanding.
  arXiv  Detail & Related papers  (2025-05-26T17:56:30Z)
• Agentic 3D Scene Generation with Spatially Contextualized VLMs [67.31920821192323]
  We introduce a new paradigm that enables vision-language models to generate, understand, and edit complex 3D environments.<n>We develop an agentic 3D scene generation pipeline in which the VLM iteratively reads from and updates the spatial context.<n>Results show that our framework can handle diverse and challenging inputs, achieving a level of generalization not observed in prior work.
  arXiv  Detail & Related papers  (2025-05-26T15:28:17Z)
• Memory-based Adapters for Online 3D Scene Perception [71.71645534899905]
  Conventional 3D scene perception methods are offline, i.e., take an already reconstructed 3D scene geometry as input. We propose an adapter-based plug-and-play module for the backbone of 3D scene perception model. Our adapters can be easily inserted into mainstream offline architectures of different tasks and significantly boost their performance on online tasks.
  arXiv  Detail & Related papers  (2024-03-11T17:57:41Z)

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.