Today for AI
HOT RADAR
opensourceHEAT 9.1°

AI CURATED HOT STORY · 11/9/2026

Tsinghua Open-Sources OpenMise to Give Video Models 3D Spatial Memory

1 reports archived1 independent sourcesupdated 11/9/2026, 12:56:00
Synthesis & Latest Updates
1 Sources Cross-Validated

A Tsinghua and University of Pennsylvania team has open-sourced OpenMise, a spatial scene editing toolkit positioned as a bridge between agents and 3D scenes. It splits hard video generation into two simpler stages, building an editable 3D scene first and rendering video second, fixing detail drift such as misplaced chess pieces or clipping and cutting repeated re-rolls.

LATEST/A Tsinghua and University of Pennsylvania team has open-sourced OpenMise, a spatial scene editing toolkit positioned as a bridge between agents and 3D scenes. It splits hard video generation into two simpler stages, building an editable 3D scene first and rendering video second, fixing detail drift such as misplaced chess pieces or clipping and cutting repeated re-rolls.

Hourly heat curve

14 fully observed hours
Now
9.1
Peak
12.013:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first
  1. 新智元 (微信公众号)T2·74 pts

    Tsinghua Open-Sources OpenMise to Give Video Models 3D Spatial Memory

    • Splits generation into 3D scene construction and rendering to enforce cross-frame consistency via explicit spatial state
    • Targets the re-roll pain of frontier models on precise motion and spatial relations, cutting regeneration compute
    • Ships as an agent-callable spatial scene editing tool that can act as a planning layer before video generation