SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning

• URL: http://arxiv.org/abs/2603.22057v1
• Date: Mon, 23 Mar 2026 14:54:34 GMT
• Title: SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning
• Abstract summary: We propose a framework that enhances the spatial awareness of pre-trained vision encoders by injecting 3D spatial knowledge expressed in linguistic descriptions.<n>The core idea involves converting dense 3D spatial information from 2D images into linguistic expressions.<n>We adopt a multi-turn Chain-of-Thought reasoning process that progressively incorporates dense spatial knowledge and builds hierarchical spatial understanding.
• Score: 54.63188577755209
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the remarkable success of large-scale pre-trained image representation models (i.e., vision encoders) across various vision tasks, they are predominantly trained on 2D image data and therefore often fail to capture 3D spatial relationships between objects and backgrounds in the real world, constraining their effectiveness in many downstream applications. To address this, we propose SpatialBoost, a scalable framework that enhances the spatial awareness of existing pre-trained vision encoders by injecting 3D spatial knowledge expressed in linguistic descriptions. The core idea involves converting dense 3D spatial information from 2D images into linguistic expressions, which is then used to inject such spatial knowledge into vision encoders through a Large Language Model (LLM). To this end, we adopt a multi-turn Chain-of-Thought (CoT) reasoning process that progressively incorporates dense spatial knowledge and builds hierarchical spatial understanding. To validate effectiveness, we adapt SpatialBoost to state-of-the-art vision encoders such as DINOv3, and evaluate its performance gains on a wide range of benchmarks requiring both 3D perception and general vision abilities. For instance, SpatialBoost improves DINOv3 performance from 55.9 to 59.7 mIoU on ADE20K, achieving state-of-the-art performance with 3.8% gain over the pre-trained DINOv3.

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)
• PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction [57.63073414949329]
  We propose PointACT, a dual-system 3D-aware VLA policy that integrates hierarchical 3D point cloud representations directly into the action decoding process.<n>PointACT employs a multi-scale point-action interaction mechanism with efficient bottleneck window self-attention, enabling evolving action tokens to densely attend to both local geometric detail and global scene structure.
  arXiv  Detail & Related papers  (2026-05-20T17:10:31Z)
• Geometry-Guided 3D Visual Token Pruning for Video-Language Models [35.786221225043455]
  We propose Geo3DPruner, a Geometry-Guided 3D Visual Token Pruning framework.<n>Geo3DPruner first models cross-frame relevance through geometry-aware global attention, and then performs a two-stage pruning process.<n>Experiments on multiple 3D scene understanding benchmarks demonstrate that Geo3DPruner retains over 90% of the original performance while pruning 90% of visual tokens, significantly outperforming existing text-guided and vision-guided pruning methods.
  arXiv  Detail & Related papers  (2026-04-20T13:33:50Z)
• 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)
• Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting [64.64738535860351]
  We present a scalable pipeline that converts single-view images into comprehensive, scale- and appearance-realistic 3D representations.<n>Our method bridges the gap between the vast repository of imagery and the increasing demand for spatial scene understanding.<n>By automatically generating authentic, scale-aware 3D data from images, we significantly reduce data collection costs and open new avenues for advancing spatial intelligence.
  arXiv  Detail & Related papers  (2025-07-24T14:53:26Z)
• HSENet: Hybrid Spatial Encoding Network for 3D Medical Vision-Language Understanding [11.482339306296204]
  We present a framework that exploits 3D medical visual cues by effective visual perception and projection for accurate and robust vision-language understanding.<n>Specifically, HSENet employs dual-3D vision encoders to perceive both global volumetric contexts and fine-grained anatomical details.<n>We also propose Spatial Packer, an efficient multimodal projector that condenses high-resolution 3D spatial regions into a compact set of informative visual tokens.
  arXiv  Detail & Related papers  (2025-06-11T11:46:57Z)
• 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)
• BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence [11.91274849875519]
  We introduce a novel image-centric 3D perception model, BIP3D, to overcome the limitations of point-centric methods.<n>We leverage pre-trained 2D vision foundation models to enhance semantic understanding, and introduce a spatial enhancer module to improve spatial understanding.<n>In our experiments, BIP3D outperforms current state-of-the-art results on the EmbodiedScan benchmark, achieving improvements of 5.69% in the 3D detection task and 15.25% in the 3D visual grounding task.
  arXiv  Detail & Related papers  (2024-11-22T11:35:42Z)
• CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data [80.42480679542697]
  We propose Contrastive Language-Image-Point Cloud Pretraining (CLIP$2$) to learn the transferable 3D point cloud representation in realistic scenarios. Specifically, we exploit naturally-existed correspondences in 2D and 3D scenarios, and build well-aligned and instance-based text-image-point proxies from those complex scenarios.
  arXiv  Detail & Related papers  (2023-03-22T09:32:45Z)

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.