CVNov 20, 2025

Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning

arXiv:2511.16160v12 citationsh-index: 14Has Code
Originality Incremental advance
AI Analysis

This work addresses fine-grained spatial reasoning for MLLMs, offering a novel method to enhance quantitative spatial computation, though it is incremental relative to existing cognitive map approaches.

The paper tackles the limitation of grid-based cognitive maps for spatial reasoning in Multimodal Large Language Models by proposing Video2Layout, a framework that reconstructs metric-grounded spatial layouts from video using continuous object boundary coordinates. The model, V2LO-7B, achieves an average improvement of 4.92% over grid-based methods on benchmarks, validating its superiority.

Spatial intelligence is a critical frontier for Multimodal Large Language Models (MLLMs), empowering them to comprehend the physical world. Drawing inspiration from human perception mechanisms, existing studies attempt to construct a coherent spatial understanding via grid-based cognitive maps from multi-frame visual inputs. However, current grid-based map methods rely on discretized raster representations, which limit the model's ability in fine-grained spatial reasoning. To overcome this limitation, we propose Video2Layout, a framework for reconstructing metric-grounded spatial layouts from video. The framework employs continuous object boundary coordinates to quantify inter-object physical distances and object size. This empowers the model with quantitative spatial computation capabilities, effectively alleviating the inherent ambiguity when describing spatial relationships in natural language. Specifically, our method comprises two core stages. First, in supervised fine-tuning stage, we construct a high-quality dataset from the AI2THOR simulator, which enables the model to learn the mapping from visual inputs to precise boundary coordinates. Subsequently, a reinforcement fine-tuning stage further enhances the model's real-world generalization capabilities. To systematically evaluate the correlation between cognitive map accuracy and image quantity, as well as how the quantity of image inputs affects spatial reasoning accuracy, we introduce QVS-Bench, a diagnostic benchmark designed to analyze the relevant mechanisms. Evaluated on QVS-Bench and mainstream spatial reasoning benchmarks, our model, V2LO-7B achieves an average improvement of 4.92% over the model trained on grid maps, validating the superiority of our method. Our code is available at https://github.com/ybrrraway/Video2Layout.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes