Passive non-line-of-sight (NLOS) imaging has witnessed rapid development in recent years, due to its ability to image objects that are out of sight. The light transport condition plays an important role in this task since changing the conditions will lead to different imaging models. Existing learning-based NLOS methods usually train independent models for different light transport conditions, which is computationally inefficient and impairs the practicality of the models. In this work, we propose NLOS-LTM, a novel passive NLOS imaging method that effectively handles multiple light transport conditions with a single network. We achieve this by inferring a latent light transport representation from the projection image and using this representation to modulate the network that reconstructs the hidden image from the projection image. We train a light transport encoder together with a vector quantizer to obtain the light transport representation. To further regulate this representation, we jointly learn both the reconstruction network and the reprojection network during training. A set of light transport modulation blocks is used to modulate the two jointly trained networks in a multi-scale way. Extensive experiments on a large-scale passive NLOS dataset demonstrate the superiority of the proposed method. The code is available at https://github.com/JerryOctopus/NLOS-LTM.

翻译：近年来，被动非视距成像因其能够对视线之外的物体进行成像而得到迅速发展。光传输条件在此任务中扮演着重要角色，因为改变条件会导致不同的成像模型。现有的基于学习的非视距方法通常针对不同的光传输条件训练独立的模型，这在计算上效率低下，并损害了模型的实用性。在本工作中，我们提出了NLOS-LTM，一种新颖的被动非视距成像方法，能够通过单一网络有效处理多种光传输条件。我们通过从投影图像推断潜在的光传输表示，并利用该表示来调制从投影图像重建隐藏图像的网络，从而实现了这一目标。我们训练一个光传输编码器与一个向量量化器共同获得光传输表示。为了进一步规范该表示，我们在训练过程中联合学习重建网络和重投影网络。一组光传输调制块被用于以多尺度方式调制这两个联合训练的网络。在大规模被动非视距数据集上进行的大量实验证明了所提方法的优越性。代码可在 https://github.com/JerryOctopus/NLOS-LTM 获取。