AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs

Erik Daxberger, Nina Wenzel, David Griffiths, Haiming Gang, Justin Lazarow, Gefen Kohavi, Kai Kang, Marcin Eichner, Yinfei Yang, Afshin Dehghan, Peter Grasch

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 48 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add multi-view input (ablation)MM-Spatial-3B specialist · CA-VQA benchmark (specialist)accuracy (average): 49.4 -> 51.4Improved
add chain-of-thought depth reasoning (ablation)MM-Spatial-3B generalist · CA-VQA benchmark (generalist)accuracy (average): 47.0 -> 49.1Improved
add GT depth via tool-use (ablation)MM-Spatial-3B specialist · CA-VQA benchmark (specialist)accuracy (average): 49.4 -> 54.5Improved
add fully encoded GT depth maps (ablation)MM-Spatial-3B specialist · CA-VQA benchmark (specialist)accuracy (average): 49.4 -> 49.9No clear effect
add monocular depth via tool-use (ablation)MM-Spatial-3B specialist · CA-VQA benchmark (specialist)accuracy (average): 49.4 -> 49.5No clear effect
use GT depth tool instead of fully encoded depth (ablation)MM-Spatial-3B specialist · CA-VQA benchmark (specialist)accuracy (average): 49.9 -> 54.5Improved
use CoT instead of monocular depth tool (ablation)MM-Spatial-3B specialist · CA-VQA benchmark (specialist)accuracy (average): 49.5 -> 50.8Improved
add multi-view to GT depth tool (ablation)MM-Spatial-3B specialist · CA-VQA benchmark (specialist)accuracy (average): 54.5 -> 55.3Improved
add image input (vs blind eval) (ablation)MM-Spatial-3B specialist · CA-VQA benchmark (specialist)accuracy (average): 24.0 -> 49.4Improved
add scale augmentation to CA-VQA* (ablation)MM-Spatial-3B + Depth (Tool; Mon.) · SpatialRGPT-Bench (average)accuracy: 74.9 -> 77.7Improved
add OSD to CA-VQA* training data (ablation)MM-Spatial-3B + Depth (Tool; Mon.) · SpatialRGPT-Bench (average)accuracy: 74.9 -> 81.0Improved
add monocular metric depth via tool-use (ablation)MM-Spatial-3B (CA-VQA* + OSD) · SpatialRGPT-Bench (average)accuracy: 77.8 -> 81.0Improved

Later papers that compared with this method

1 later accepted paper reports MM-Spatial-3B as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy