FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction
Existing learning-based occupancy prediction methods rely on large-scale 3D annotations and generalize poorly across environments. We present FreeOcc, a training-free framework for open-vocabulary occupancy prediction from monocular or RGB-D sequences. Unlike prior approaches that require voxel-level supervision and ground-truth camera poses, FreeOcc operates without 3D annotations, pose ground truth, or any learning stage. FreeOcc incrementally builds a globally consistent occupancy map via a four-layer pipeline: a SLAM backbone estimates poses and sparse geometry; a geometrically consistent Gaussian update constructs dense 3D Gaussian maps; open-vocabulary semantics from off-the-shelf v...
| Authors | Zeyu Jiang, Changqing Zhou, Xingxing Zuo et al. |
|---|---|
| Primary category | cs.RO |
| Published | 30 April 2026 |
| Last updated at source | 30 April 2026 |
Models and datasets referencing this paper
- the-masses/ReplicaOccDataset
- moreba/ReplicaOccDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.