Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning

• URL: http://arxiv.org/abs/2604.06725v1
• Date: Wed, 08 Apr 2026 06:47:55 GMT
• Title: Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning
• Abstract summary: We propose a textittraining-free framework that introduces a Visual Chain-of-Thought mechanism grounded in explicit 3D reconstruction.<n>The framework outperforms specialized spatial models and general-purpose MLLMs on major benchmarks such as 3DSRBench and Rel3D.
• Score: 10.542346290671114
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although Multimodal Large Language Models have achieved remarkable progress, they still struggle with complex 3D spatial reasoning due to the reliance on 2D visual priors. Existing approaches typically mitigate this limitation either through computationally expensive post-training procedures on limited 3D datasets or through rigid tool-calling mechanisms that lack explicit geometric understanding and viewpoint flexibility. To address these challenges, we propose a \textit{training-free} framework that introduces a Visual Chain-of-Thought mechanism grounded in explicit 3D reconstruction. The proposed pipeline first reconstructs a high-fidelity 3D mesh from a single image using MLLM-guided keyword extraction and mask generation at multiple granularities. Subsequently, the framework leverages an external knowledge base to iteratively compute optimal camera extrinsic parameters and synthesize novel views, thereby emulating human perspective-taking. Extensive experiments demonstrate that the proposed approach significantly enhances spatial comprehension. Specifically, the framework outperforms specialized spatial models and general-purpose MLLMs, including \textit{GPT-5.2} and \textit{Gemini-2.5-Flash}, on major benchmarks such as 3DSRBench and Rel3D.

Related papers

• SpatialSV: Internalizing Interpretable 3D Spatial Awareness in MLLMs via Task-Oriented Visual Supervision [12.336413790708738]
  spatial intelligence of large language models (MLLMs) is crucial for understanding and interacting with the 3D world.<n>We propose SpatialSV, a framework designed to internalize robust 3D spatial awareness within MLLMs while simultaneously offering inherent interpretability.
  arXiv  Detail & Related papers  (2026-06-18T08:09:32Z)
• EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers [6.781951702759721]
  EVA01 is a framework that extends the modality boundary of Multimodal Large Language Models.<n>It incorporates 3D mesh understanding, generation, and context-aware editing.<n>Results show that EVA01 achieves state-of-the-art native text-to-3D generation fidelity.
  arXiv  Detail & Related papers  (2026-05-16T01:55:03Z)
• Ψ-Map: Panoptic Surface Integrated Mapping Enables Real2Sim Transfer [24.777932568749446]
  We propose a comprehensive framework that integrates geometric reinforcement, end-to-end panoptic learning, and efficient rendering.<n>Our system achieves superior geometric and panoptic reconstruction quality in large-scale scenes while maintaining an inference rate exceeding 40 FPS.
  arXiv  Detail & Related papers  (2026-04-13T04:41:00Z)
• 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)
• GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models [70.61152292499737]
  We argue that this gap does not arise from insufficient geometric priors, but from a misalignment in the training paradigm.<n>Existing approaches typically resort to naive feature concatenation and optimize directly for downstream tasks without geometry-specific supervision.<n>We propose GAP-MLLM, a Geometry-Aligned Pre-training paradigm that explicitly activates structural perception before downstream adaptation.
  arXiv  Detail & Related papers  (2026-03-17T12:43:48Z)
• SpatialMosaic: A Multiview VLM Dataset for Partial Visibility [25.874299974251965]
  We propose a scalable multi-view data generation and annotation pipeline that constructs realistic spatial reasoning QAs.<n>We introduce SpatialMosaic-Bench, a benchmark for evaluating multi-view spatial reasoning under realistic and challenging scenarios.<n>We also present SpatialMosaicVLM, a hybrid framework that integrates 3D reconstruction models as geometry encoders within Vision-Language Models.
  arXiv  Detail & Related papers  (2025-12-29T10:48:54Z)
• S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance [20.55536735670125]
  3D Visual Grounding (3DVG) focuses on locating objects in 3D scenes based on natural language descriptions.<n>Recent advances in Multi-modal Large Language Models (MLLMs) have motivated research into extending them to 3DVG.<n>We propose S$2$-MLLM, an efficient framework that enhances spatial reasoning in MLLMs through implicit spatial reasoning.
  arXiv  Detail & Related papers  (2025-12-01T03:08:34Z)
• Video Spatial Reasoning with Object-Centric 3D Rollout [58.12446467377404]
  We propose Object-Centric 3D Rollout (OCR) to enable robust video spatial reasoning.<n>OCR introduces structured perturbations to the 3D geometry of selected objects during training.<n>OCR compels the model to reason holistically across the entire scene.
  arXiv  Detail & Related papers  (2025-11-17T09:53:41Z)
• MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts [50.37005070020306]
  MoRE is a dense 3D visual foundation model based on a Mixture-of-Experts (MoE) architecture.<n>MoRE incorporates a confidence-based depth refinement module that stabilizes and refines geometric estimation.<n>It integrates dense semantic features with globally aligned 3D backbone representations for high-fidelity surface normal prediction.
  arXiv  Detail & Related papers  (2025-10-31T06:54:27Z)
• IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction [82.53307702809606]
  Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions.<n>We propose InstanceGrounded Geometry Transformer (IGGT) to unify the knowledge for both spatial reconstruction and instance-level contextual understanding.
  arXiv  Detail & Related papers  (2025-10-26T14:57:44Z)
• OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion [89.98812408058336]
  We introduce textbfOpenInsGaussian, an textbfOpen-vocabulary textbfInstance textbfGaussian segmentation framework with Context-aware Cross-view Fusion.<n>OpenInsGaussian achieves state-of-the-art results in open-vocabulary 3D Gaussian segmentation, outperforming existing baselines by a large margin.
  arXiv  Detail & Related papers  (2025-10-21T03:24:12Z)
• Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation [23.359745449828363]
  We propose VLM3D, a novel text-to-3D generation framework.<n>It integrates large vision-language models into the Score Distillation Sampling pipeline as differentiable semantic and spatial priors.<n>VLM3D significantly outperforms prior SDS-based methods in semantic fidelity, geometric coherence, and spatial correctness.
  arXiv  Detail & Related papers  (2025-09-19T08:54:52Z)
• SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting [85.87902260102652]
  We introduce the novel task of Sequential 3D Gaussian Affordance Reasoning.<n>We then propose SeqSplatNet, an end-to-end framework that directly maps an instruction to a sequence of 3D affordance masks.<n>Our method sets a new state-of-the-art on our challenging benchmark, effectively advancing affordance reasoning from single-step interactions to complex, sequential tasks at the scene level.
  arXiv  Detail & Related papers  (2025-07-31T17:56:55Z)
• Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence [13.168559963356952]
  We present Spatial-MLLM, a novel framework for visual-based spatial reasoning from purely 2D observations.<n>Our key insight is to unleash the strong structure prior to the feed-forward visual geometry foundation model.<n>A connector then integrates both features into unified visual tokens for enhanced spatial understanding.
  arXiv  Detail & Related papers  (2025-05-29T17:59:04Z)

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.