DeepMind Releases GenCeption
minchoi · x · 2026-07-16
Google DeepMind released GenCeption, a system that turns videos into a searchable 4D world.
It can output multiple visual/geometric representations from the same model, including depth, segmentation, 3D keypoints, etc., and supports retrieving objects within the reconstructed 4D scene. The post also showcases 8 examples, emphasizing its ability to serve both human and robotic scenarios simultaneously.
Related event: DeepMind’s GenCeption Turns Video Into Searchable 4D Scenes(9 posts)→
More from Multimodal
- Midjourney style code share: --sref 2912175708 — tisch_eins · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- MiniMax H3 MAX nails cooking anime clips: 15-second curry demo with prompts shared — Hailuo_AI · 2026-09-11
- MiniMax Music Production Toolkit 2.5 for ComfyUI adds full mastering chain — Vivid_Promise1700 · 2026-09-11
- New Node Finder for ComfyUI ranks fresh nodes by star velocity and recency — Luke2642 · 2026-09-11
- Using a finisher move on one mosquito with MiniMax H3 MAX — the bug survives — Hailuo_AI · 2026-09-11