LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering

Semantic occupancy has recently gained significant traction as a prominent method for 3D scene representation. However, most existing camera-based methods rely on costly datasets with fine-grained 3D voxel labels or LiDAR scans for training, which limits their practicality and scalability, raising the need for self-supervised approaches in this domain. Moreover, most methods are tied to a predefined set of classes which they can detect. In this work we present a novel approach for open vocabulary occupancy estimation called \textit{LangOcc}, that is trained only via camera images, and can detect arbitrary semantics via vision-language alignment. In particular, we distill the knowledge of the strong vision-language aligned encoder CLIP into a 3D occupancy model via differentiable volume rendering. Our model estimates vision-language aligned features in a 3D voxel grid using only images. It is trained in a self-supervised manner by rendering our estimations back to 2D space, where ground-truth features can be computed. This training mechanism automatically supervises the scene geometry, allowing for a straight-forward and powerful training method without any explicit geometry supervision. LangOcc outperforms LiDAR-supervised competitors in open vocabulary occupancy by a large margin, solely relying on vision-based training. We also achieve state-of-the-art results in self-supervised semantic occupancy estimation on the Occ3D-nuScenes dataset, despite not being limited to a specific set of categories, thus demonstrating the effectiveness of our proposed vision-language training.