GenCine: Single-Image Video Generation with 3D Motion Control

A Johns Hopkins team open-sourced GenCine, which generates videos from a single image with precise local 3D control over camera and object motion, outperforming baseline methods, with all training done on academic compute and technical details published.

2026-10-03 ~ 2026-10-03 · 3 related posts

• JHU's GenCine turns a single image into an editable 3D scene for camera and object motion control in video generation — anand_bhattad · 2026-10-03
• GenCine comparisons show 3D controls guiding a robot arm where baselines barely move — anand_bhattad · 2026-10-03
• GenCine was trained on academic compute: full technical details now on the project page — anand_bhattad · 2026-10-03