HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models

• URL: http://arxiv.org/abs/2603.25411v1
• Date: Thu, 26 Mar 2026 13:08:12 GMT
• Title: HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models
• Abstract summary: We propose a principled hierarchical framework that decomposes the learning of 3D spatial understanding in vision-language models into four progressively complex levels.<n>We develop an RGB-D VLM incorporating metric-scale point maps as auxiliary inputs to further enhance spatial understanding.
• Score: 33.677114670148235
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Achieving human-like spatial intelligence for vision-language models (VLMs) requires inferring 3D structures from 2D observations, recognizing object properties and relations in 3D space, and performing high-level spatial reasoning. In this paper, we propose a principled hierarchical framework that decomposes the learning of 3D spatial understanding in VLMs into four progressively complex levels, from geometric perception to abstract spatial reasoning. Guided by this framework, we construct an automated pipeline that processes approximately 5M images with over 45M objects to generate 3D spatial VQA pairs across diverse tasks and scenes for VLM supervised fine-tuning. We also develop an RGB-D VLM incorporating metric-scale point maps as auxiliary inputs to further enhance spatial understanding. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on multiple spatial understanding and reasoning benchmarks, surpassing specialized spatial models and large proprietary systems such as Gemini-2.5-pro and GPT-5. Moreover, our analysis reveals clear dependencies among hierarchical task levels, offering new insights into how multi-level task design facilitates the emergence of 3D spatial intelligence.

Related papers

• Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models [32.477423778941386]
  We present GeoVR, a framework that learns geometric representations using purely 2D video sequences.<n>Rather than employing superficial feature mixing, GeoVR reshapes the internal representations of the MLLM by distilling geometry knowledge.<n>Experiments on spatial reasoning benchmarks demonstrate that GeoVR achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-06-04T08:11:12Z)
• GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation [75.85672467847631]
  We introduce the Geometry-Aware BEV (GA-BEV) - a compact, 3D-grounded feature representation.<n>We construct BEV spatial maps from RGB-D inputs by projecting visual features into 3D space.<n>We incorporate features from a pretrained 3D foundation model into the BEV space, injecting structural priors learned from large-scale 3D reconstruction tasks.
  arXiv  Detail & Related papers  (2026-05-21T06:20:17Z)
• Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models [79.18306680174011]
  DSR Suite bridges gap across aspects of dataset, benchmark and model.<n>We propose an automated pipeline that generates multiple-choice question-answer pairs from in-the-wild videos for DSR.<n>The pipeline extracts rich geometric and motion information, including camera poses, local point clouds, object masks, orientations, and 3D trajectories.
  arXiv  Detail & Related papers  (2025-12-23T17:56:36Z)
• Abstract 3D Perception for Spatial Intelligence in Vision-Language Models [100.13033631690114]
  Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding.<n>We introduce SandboxVLM, a framework that leverages abstract bounding boxes to encode geometric structure and physical kinematics for VLM.<n>Our approach consistently improves spatial intelligence, achieving an 8.3% gain on SAT Real compared with baseline methods.
  arXiv  Detail & Related papers  (2025-11-14T04:16:09Z)
• SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards [37.39035418889281]
  We introduce SpatialThinker, a 3D-aware MLLM trained with RL to integrate structured spatial grounding with multi-step reasoning.<n>The model simulates human-like spatial perception by constructing a scene graph of task-relevant objects and spatial relations, and reasoning towards an answer via dense spatial rewards.
  arXiv  Detail & Related papers  (2025-11-10T18:52:47Z)
• Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning [1.5604334108839177]
  Vision-language models (VLMs) have advanced multimodal reasoning but still face challenges in spatial reasoning for 3D scenes and complex object configurations.<n>We introduce SpatialViLT, an enhanced VLM that integrates spatial features like depth maps, 3D coordinates, and edge maps through a multi-task learning framework.<n>We propose two variants: SpatialViLT and MaskedSpatialViLT, focusing on full and masked object regions, respectively.<n>Our models excel in spatial reasoning categories such as directional, topological, and proximity relations, as demonstrated on the challenging Visual Spatial Reasoning (VSR) dataset.
  arXiv  Detail & Related papers  (2025-10-03T19:04:15Z)
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models [68.46716645478661]
  Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content.<n>Current VLMs excel primarily at egocentric spatial reasoning (from the camera's perspective) but fail to generalize to allocentric viewpoints.<n>We introduce ViewSpatial-Bench, the first comprehensive benchmark designed specifically for multi-viewpoint spatial localization recognition evaluation.
  arXiv  Detail & Related papers  (2025-05-27T17:59:26Z)
• 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)
• SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors [42.85605789984155]
  Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA) We present SpatialPIN, a framework designed to enhance the spatial reasoning capabilities of VLMs through prompting and interacting with priors from multiple 3D foundation models in a zero-shot, training-free manner. Our spatial reasoning-imbued VLM performs well on various forms of spatial VQA and can extend to help in various downstream robotics tasks such as pick and stack and trajectory planning.
  arXiv  Detail & Related papers  (2024-03-18T17:38:29Z)

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.