Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models

• URL: http://arxiv.org/abs/2512.20557v1
• Date: Tue, 23 Dec 2025 17:56:36 GMT
• Title: Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models
• Authors: Shengchao Zhou, Yuxin Chen, Yuying Ge, Wei Huang, Jiehong Lin, Ying Shan, Xiaojuan Qi,
• Abstract summary: 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.
• Score: 79.18306680174011
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relationship in 3D space over time, largely due to the scarcity of scalable 4D-aware training resources. To bridge this gap across aspects of dataset, benchmark and model, we introduce DSR Suite. First, we propose an automated pipeline that generates multiple-choice question-answer pairs from in-the-wild videos for DSR. By leveraging modern vision foundation models, the pipeline extracts rich geometric and motion information, including camera poses, local point clouds, object masks, orientations, and 3D trajectories. These geometric cues enable the construction of DSR-Train for learning and further human-refined DSR-Bench for evaluation. Compared with previous works, our data emphasize (i) in-the-wild video sources, (ii) object- and scene-level 3D requirements, (iii) viewpoint transformations, (iv) multi-object interactions, and (v) fine-grained, procedural answers. Beyond data, we propose a lightweight Geometry Selection Module (GSM) to seamlessly integrate geometric priors into VLMs, which condenses question semantics and extracts question-relevant knowledge from pretrained 4D reconstruction priors into a compact set of geometry tokens. This targeted extraction avoids overwhelming the model with irrelevant knowledge. Experiments show that integrating DSR-Train and GSM into Qwen2.5-VL-7B significantly enhances its dynamic spatial reasoning capability, while maintaining accuracy on general video understanding benchmarks.

Related papers

• Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video [76.32954467706581]
  We propose SAGE, a framework for Scalable Adaptation of GEometric foundation models from raw video streams.<n>We use a hierarchical mining pipeline to transform videos into training trajectories and hybrid supervision.<n>Experiments show that SAGE significantly enhances zero-shot generalization, reducing Chamfer Distance by 20-42% on unseen benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T09:53:21Z)
• 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)
• 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)
• 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)
• Easi3R: Estimating Disentangled Motion from DUSt3R Without Training [69.51086319339662]
  We introduce Easi3R, a simple yet efficient training-free method for 4D reconstruction.<n>Our approach applies attention adaptation during inference, eliminating the need for from-scratch pre-training or network fine-tuning.<n>Our experiments on real-world dynamic videos demonstrate that our lightweight attention adaptation significantly outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-31T17:59:58Z)

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.