GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models

• URL: http://arxiv.org/abs/2603.16461v1
• Date: Tue, 17 Mar 2026 12:43:48 GMT
• Title: GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models
• Abstract summary: 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.
• Score: 70.61152292499737
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging implicit geometric priors from 3D reconstruction models, image-based methods still exhibit a notable performance gap compared to methods using explicit 3D data. We argue that this gap does not arise from insufficient geometric priors, but from a misalignment in the training paradigm: text-dominated fine-tuning fails to activate geometric representations within MLLMs. Existing approaches typically resort to naive feature concatenation and optimize directly for downstream tasks without geometry-specific supervision, leading to suboptimal structural utilization. To address this limitation, we propose GAP-MLLM, a Geometry-Aligned Pre-training paradigm that explicitly activates structural perception before downstream adaptation. Specifically, we introduce a visual-prompted joint task that compels the MLLMs to predict sparse pointmaps alongside semantic labels, thereby enforcing geometric awareness. Furthermore, we design a multi-level progressive fusion module with a token-level gating mechanism, enabling adaptive integration of geometric priors without suppressing semantic reasoning. Extensive experiments demonstrate that GAP-MLLM significantly enhances geometric feature fusion and consistently enhances performance across 3D visual grounding, 3D dense captioning, and 3D video object detection tasks.

Related papers

• GeoAlign: Geometric Feature Realignment for MLLM Spatial Reasoning [12.641199394796436]
  Multimodal large language models (MLLMs) have exhibited remarkable performance in various visual tasks, yet still struggle with spatial reasoning.<n>Recent efforts mitigate this by injecting geometric features from 3D foundation models, but rely on static single-layer extractions.<n>We propose GeoAlign, a novel framework that dynamically aggregates multi-layer geometric features to realign with the actual demands.
  arXiv  Detail & Related papers  (2026-04-14T11:58:02Z)
• Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning [10.542346290671114]
  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.
  arXiv  Detail & Related papers  (2026-04-08T06:47:55Z)
• Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs [13.627465963609936]
  GUIDE (Geometric Unrolling Inside MLLM Early-layers) is a progressive geometric priors injection framework.<n>We introduce a context-aware gating that enables the model to fetch requisite spatial cues based on current semantics.
  arXiv  Detail & Related papers  (2026-04-07T10:45:28Z)
• 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)
• Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations [22.197086495542816]
  We introduce geometrically referenced 3D scene representations (GR3D)<n> GR3D annotates objects in the images with unique IDs and encodes their 3D geometric attributes as textual references indexed by these IDs.<n>This representation enables MLLMs to interpret 3D cues using their advanced language-based skills in mathematical reasoning.
  arXiv  Detail & Related papers  (2026-03-09T16:42:43Z)
• GLaD: Geometric Latent Distillation for Vision-Language-Action Models [106.53332923530245]
  We introduce GLaD, a geometry-aware Vision-Language-Action (VLA) framework that incorporates 3D geometric priors during pretraining through knowledge distillation.<n>GLaD achieves 94.1% average success rate across four LIBERO task suites, outperforming UniVLA (92.5%) which uses identical pretraining data.
  arXiv  Detail & Related papers  (2025-12-10T13:07:27Z)
• 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)
• 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)
• Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification [59.17489431187807]
  We propose a framework that enhances 3D geometric fidelity by leveraging CLIP's hierarchical spatial semantics.<n>Our method significantly improves 3D few-shot class-incremental learning, achieving superior geometric coherence and robustness to texture bias.
  arXiv  Detail & Related papers  (2025-09-18T13:45:08Z)
• Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model [51.02616473941499]
  3D object segmentation with Large Language Models (LLMs) has become a prevailing paradigm due to its broad semantics, task flexibility, and strong generalization.<n>However, this paradigm is hindered by representation misalignment: LLMs process high-level semantic tokens, whereas 3D point clouds convey only dense geometric structures.<n>We present the Point Linguist Model (PLM), a general framework that bridges the representation gap between LLMs and dense 3D point clouds.
  arXiv  Detail & Related papers  (2025-09-09T15:01:28Z)
• 3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation [17.294440057314812]
  Vision-Language Models (VLMs) have shown remarkable performance on diverse visual and linguistic tasks.<n>We propose Geometric Distillation, a framework that injects human-inspired geometric cues into pretrained VLMs.<n>Our method shapes representations to be geometry-aware while remaining compatible with natural image-text inputs.
  arXiv  Detail & Related papers  (2025-06-11T15:56:59Z)

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.