SOURCE-LINKED INTELLIGENCE

Exploring 2D backbone effects for indoor semantic occupancy prediction

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Semantic occupancy prediction gives an embodied agent a voxel-level account of where space is free, occupied, and semantically meaningful. In RGB-D pipelines such as EmbodiedScan, the image encoder is often left as a default module, even though its features are the visual evidence later sampled into the 3D grid. We study this design choice directly. A central finding is that changing the 2D backbone improves occupancy accuracy more than several carefully designed occupancy architectures or modules. We keep the main RGB-D projection, depth branch, and occupancy head fixed, and replace only the

Read original source ↗ Open in workspace

recordType

paper

region

Global