Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

ICLR 2026 Conference Submission300 Authors

Keywords: Unified Multimodal Model, Spatial Intelligence, Controllable Generation, Camera Calibration

TL;DR: We make the first attempt to unify camera-centric understanding and generation in a cohesive multimodal framework.

Abstract: Camera-centric understanding and generation are two cornerstones of spatial intelligence, yet they are typically studied in isolation. We present Puffin, a unified camera-centric multimodal model that extends spatial awareness along the camera dimension. Puffin integrates language regression and diffusion-based generation to interpret and create scenes from arbitrary viewpoints. To bridge the modality gap between cameras and vision-language, we introduce a novel paradigm that treats camera as language, enabling thinking with camera. This guides the model to align spatially grounded visual cues with photographic terminology while reasoning across geometric context. Puffin is trained on Puffin-4M, a large-scale dataset of 4 million vision-language-camera triplets. We incorporate both global camera parameters and pixel-wise camera maps, yielding flexible and reliable spatial generation. Experiments demonstrate Puffin’s superior performance over specialized models for camera-centric generation and understanding. With instruction tuning, Puffin generalizes to diverse cross-view tasks such as spatial imagination, world exploration, and photography guidance. We will release the code, models, dataset pipeline, and benchmark to advance multimodal spatial intelligence research.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 300