Skip to content
RobotWorld
← Back

DeWorldSG: depth-aware 3D scene graph generation

Loading video
Loading video

DeWorldSG (ECCV 2026) generates spatio-temporally consistent 3D semantic scene graphs from RGB-D sequences by combining depth-aware probabilistic object modeling with world-model-guided priors.

Category: perception
Author: @rsasaki0109
Date: 2026-08-13T00:00:00
Duration: 75.633s