media creative tools
The Video World Remembers Its Walls as Planes
PPMem stores generated scenes as a compact set of oriented surfaces, then renders that memory back into later video chunks.
Summary
PPMem stores generated scenes as a compact set of oriented surfaces, then renders that memory back into later video chunks.
Long generated worlds drift because the model lacks a persistent geometric record of what it already made. PPMem adds a plane-prediction head to a video diffusion transformer. Each chunk produces both RGB frames and planar geometry; merged planes become memory that later chunks receive as rendered depth. The authors report that the representation is roughly three orders of magnitude more compact than per-pixel point clouds and sustains coherence across hundreds of frames while also yielding depth, normals and exportable surfaces. Results on DL3DV and RealEstate10K beat compared 3D-grounded world models on reported video quality. Plane-heavy scenes are a favorable abstraction, so the approach is not a complete memory for every object or environment.
Why it matters
PPMem stores generated scenes as a compact set of oriented surfaces, then renders that memory back into later video chunks.
Limits and context
- Plane-heavy scenes are a favorable abstraction, so the approach is not a complete memory for every object or environment.
Key claims
PPMem stores generated scenes as a compact set of oriented surfaces, then renders that memory back into later video chunks.
Qualification: Plane-heavy scenes are a favorable abstraction, so the approach is not a complete memory for every object or environment.
Evidence: source-2026-10-19-009
Sources
- arXiv preprint 2610.23795, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.