LangOcc: Open Vocabulary Occupancy Estimation via Volume Rendering

The 3D occupancy estimation task has become an important challenge in the area of vision-based autonomous driving recently. However, most existing camera-based methods rely on costly 3D voxel labels or LiDAR scans for training, limiting their practicality and scalability. 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 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 weakly-supervised manner by rendering our estimations back to <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$2 D$</tex> space, where features can easily be aligned with CLIP. 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 with a mAP of 22.7 by a large margin (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$+4.3 \%$</tex>), solely relying on vision-based training. We also achieve a mIoU score of 11.84 on the Occ3D-nuScenes dataset, surpassing previous vision-only semantic occupancy estimation methods (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$+1.71 \%$</tex>), despite not being limited to a specific set of categories.