AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MonoSR: Open-Vocabulary Spatial Reasoning on Monocular Images

Qirui Wang, Jingyi He, Yining Pan, Si Yong Yeo, Xulei Yang, Shijie Li

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 8 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
fine-tune on MonoSRQwen2.5-VL-3B · MonoSR Indooroverall accuracy: 0.283 -> 0.494Improved
fine-tune on MonoSRQwen2.5-VL-3B · MonoSR Outdooroverall accuracy: 0.302 -> 0.442Improved
fine-tune on MonoSRInternVL-3.5-2B · MonoSR Indooroverall accuracy: 0.301 -> 0.483Improved
fine-tune on MonoSRInternVL-3.5-2B · MonoSR Outdooroverall accuracy: 0.294 -> 0.462Improved
add scene information (SI) text (ablation)fine-tuned VLM · MonoSR low/mid-level tasksaccuracyImproved
add 2D visual prompts (ablation)fine-tuned VLM · MonoSR mid-level indooraccuracyImproved
add 3D bounding boxes (ablation)fine-tuned VLM · MonoSRaccuracyImproved
add targeted 2D VP + 3D bbox to fine-tuned model (ablation)Qwen2.5-VL-3B · MonoSR Indooroverall accuracy: 0.494 -> 0.798Improved
provide 2D VP + 3D bbox for all objects instead of targeted (ablation)Qwen2.5-VL-3B · MonoSR Indooroverall accuracy: 0.798 -> 0.767Hurt
provide 2D VP + 3D bbox for all objects instead of targeted (ablation)InternVL-3.5-2B · MonoSR Indooroverall accuracy: 0.794 -> 0.721Hurt
fine-tune on MonoSRQwen2.5-VL-3B · MonoSR long-tail classes (bottom 20%)accuracy: 0.375 -> 0.675Improved
use stricter 5% relative error thresholdGemini-2.5-Pro · MonoSR Object-Centric Dist (Num.)accuracy: 0.305 -> 0.143Hurt

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