We propose CLIP-Fields, an implicit scene model that can be used for a variety of tasks, such as segmentation, instance identification, semantic search over space, and view localization. CLIP-Fields learns a mapping from spatial locations to semantic embedding vectors. Importantly, we show that this mapping can be trained with supervision coming only from web-image and web-text trained models such as CLIP, Detic, and Sentence-BERT; and thus uses no direct human supervision. When compared to baselines like Mask-RCNN, our method outperforms on few-shot instance identification or semantic segmentation on the HM3D dataset with only a fraction of the examples. Finally, we show that using CLIP-Fields as a scene memory, robots can perform semantic navigation in real-world environments. Our code and demonstration videos are available here: https://mahis.life/clip-fields
@article{arxiv.2210.05663,
title = {CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory},
author = {Nur Muhammad Mahi Shafiullah and Chris Paxton and Lerrel Pinto and Soumith Chintala and Arthur Szlam},
journal= {arXiv preprint arXiv:2210.05663},
year = {2024}
}
Comments
Code, video, and interactive demonstrations available at https://mahis.life/clip-fields. Accepted for publication at Robotics: Science and Systems 2023 in Daegu, Korea