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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Boeder, Simon, Gigengack, Fabian, Risse, Benjamin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917732614668288
author Boeder, Simon
Gigengack, Fabian
Risse, Benjamin
author_facet Boeder, Simon
Gigengack, Fabian
Risse, Benjamin
contents 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 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_17310
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering
Boeder, Simon
Gigengack, Fabian
Risse, Benjamin
Computer Vision and Pattern Recognition
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 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.
title LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.17310