CVPR Findings2026
COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligence
Zefeng Zhang, Xiangzhao Hao, Hengzhu Tang, Zhenyu Zhang, Jiawei Sheng, Xiaodong Li, Zhenyang Li, Li Gao, Daiting Shi, Dawei Yin, Tingwen Liu
Abstract
Visual Spatial Reasoning is crucial for enabling Multimodal Large Language Models (MLLMs) to understand object properties and spatial relationships, yet current models still struggle with 3D-aware reasoning. Existing approaches typically enhance either perception, by augmenting RGB inputs with auxiliary modalities such as depth and segmentation, or reasoning, by training on spatial VQA datasets and applying reinforcement learning, and thus treat these two aspects in isolation. In this work, we investigate whether a unified MLLM can develop an intrinsic ability to enhance spatial perception and, through adaptive interleaved reasoning, achieve stronger spatial intelligence. We propose COOPER, a unified MLLM that leverages depth and segmentation as auxiliary modalities and is trained in two stages to acquire auxiliary modality generation and adaptive, interleaved reasoning capabilities. COOPER achieves an average 6.91% improvement in spatial reasoning while maintaining general performance. Moreover, even a variant trained only for auxiliary modality generation attains a 7.92% gain on distance and size estimation, suggesting that learning to generate auxiliary modalities helps internalize spatial knowledge and strengthen spatial understanding.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- PaLM-E: An Embodied Multimodal Language Model cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis cites Scalable Diffusion Models with Transformers
Builds on45
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 5,568 citations
- Scaling Rectified Flow Transformers for High-Resolution Image SynthesisPatrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari et al.ICML 2024 · 3,620 citations
- Vision Transformers for Dense PredictionRené Ranftl, Alexey Bochkovskiy, Vladlen KoltunICCV 2021 · 2,647 citations
- PaLM-E: An Embodied Multimodal Language ModelDanny Driess, Fei Xia, Mehdi S. M. Sajjadi, Corey Lynch et al.ICML 2023 · 2,601 citations
Related papers
- Language-Image Models with 3D UnderstandingJang Hyun Cho, Boris Ivanovic, Yulong Cao, Edward Schmerling et al.ICLR 2025 · 2 citations
- SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language ModelsHongxing Li, Dingming Li, Zixuan Wang, Yuchen Yan et al.ICLR 2026 · 75 citations
- HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language ModelsHuizhi Liang, Yichao Shen, Yu Deng, Sicheng Xu et al.CVPR 2026 · 2 citations
- Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial IntelligenceDiankun Wu, Fangfu Liu, Yi-Hsin Hung, Yueqi DuanNeurIPS 2025 · 245 citations
- Actial: Activate Spatial Reasoning Ability of Multimodal Large Language ModelsXiaoyu Zhan, Wenxuan Huang, Hao Sun, Xinyu Fu et al.NeurIPS 2025 · 11 citations
