CinemaTraj: LLM Agent Plans Cinematic Camera Trajectories in 3D Scenes
joemeno · x · 2026-08-02
Researchers from TU Munich and Huawei Dresden propose CinemaTraj, a framework that reframes camera trajectory planning as language-grounded spatial reasoning. Given RGB-D images and a user prompt, an LLM agent uses a structured 3D scene graph to decompose the request into atomic cinematographic movements (dolly, orbit, crane, pan, tilt, zoom, arc), and plans collision-free trajectories. It generates cinematic videos with synchronized voiceover and subtitles, with applications in real-estate ads and virtual tours. Accepted at ACM Multimedia 2026.
More from Multimodal
- ComfyUI v0.29.0 Text Generation Bug Causes Gemma to Leak Internal Planning — jjjnnnxxx · 2026-08-02
- ByteDance's Dreamina Offers Creators Enhanced Control in AI Video Generation — aftahi_ai · 2026-08-02
- Seedance 2.5 Prompting Guides Revealed: Reference Roles, Audio Syntax, and More — LaillaElgohary · 2026-08-02
- Chinese AI Video Model 'Seedance 2.5' Tricks French News Media into Believing Fake Footage — beechinour · 2026-08-02
- Creator Shares Image Generation Results Using Midjourney — op7418 · 2026-08-02
- Krea 2 Turbo Workflow: Generates 2K Uncensored Images in 73s on RTX 5060 Ti — gabrielxdesign · 2026-08-02