arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.04748cs.CV
收藏

CLIP-FO3D:从2D密集CLIP学习免费的开放世界3D场景表示

CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP

Tsinghua University(清华大学);Xi’an Jiaotong University(西安交通大学)

Junbo Zhang, Runpei Dong, Kaisheng Ma

摘要:

训练3D场景理解模型需要复杂的人类注释,这是费力收集的,并且导致模型仅编码闭集对象语义。相比之下,视觉语言预训练模型(例如,CLIP)已经显示出显著的开放世界推理特性。为此,我们建议直接将CLIP的特征空间转换为3D场景理解模型,而无需任何形式的监督。我们首先修改CLIP的输入和转发过程,以便它可以适应于提取密集的像素特征的3D场景内容。然后,我们将多视图图像特征投影到点云上,并通过特征提取训练三维场景理解模型。在没有任何注释或额外训练的情况下,我们的模型在开放词汇语义和长尾概念上实现了有希望的无注释语义分割结果。此外,作为一个跨模态的预训练框架,我们的方法可以用来提高数据效率在微调。我们的模型在各种zero-shot和数据高效学习基准测试中优于以前的SOTA方法。最重要的是,我们的模型成功地继承了CLIP丰富的结构化知识,使3D场景理解模型不仅可以识别对象概念,还可以识别开放世界的语义。

英文摘要:

Training a 3D scene understanding model requires complicated human annotations, which are laborious to collect and result in a model only encoding close-set object semantics. In contrast, vision-language pre-training models (e.g., CLIP) have shown remarkable open-world reasoning properties. To this end, we propose directly transferring CLIP's feature space to 3D scene understanding model without any form of supervision. We first modify CLIP's input and forwarding process so that it can be adapted to extract dense pixel features for 3D scene contents. We then project multi-view image features to the point cloud and train a 3D scene understanding model with feature distillation. Without any annotations or additional training, our model achieves promising annotation-free semantic segmentation results on open-vocabulary semantics and long-tailed concepts. Besides, serving as a cross-modal pre-training framework, our method can be used to improve data efficiency during fine-tuning. Our model outperforms previous SOTA methods in various zero-shot and data-efficient learning benchmarks. Most importantly, our model successfully inherits CLIP's rich-structured knowledge, allowing 3D scene understanding models to recognize not only object concepts but also open-world semantics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑