In the absence of parallax cues, a learning-based single image depth estimation (SIDE) model relies heavily on shading and contextual cues in the image. While this simplicity is attractive, it is necessary to train such models on large and varied datasets, which are difficult to capture. It has been shown that using embeddings from pre-trained foundational models, such as CLIP, improves zero shot transfer in several applications. Taking inspiration from this, in our paper we explore the use of global image priors generated from a pre-trained ViT model to provide more detailed contextual information. We argue that the embedding vector from a ViT model, pre-trained on a large dataset, captures greater relevant information for SIDE than the usual route of generating pseudo image captions, followed by CLIP based text embeddings. Based on this idea, we propose a new SIDE model using a diffusion backbone which is conditioned on ViT embeddings. Our proposed design establishes a new state-of-the-art (SOTA) for SIDE on NYUv2 dataset, achieving Abs Rel error of 0.059(14% improvement) compared to 0.069 by the current SOTA (VPD). And on KITTI dataset, achieving Sq Rel error of 0.139 (2% improvement) compared to 0.142 by the current SOTA (GEDepth). For zero-shot transfer with a model trained on NYUv2, we report mean relative improvement of (20%, 23%, 81%, 25%) over NeWCRFs on (Sun-RGBD, iBims1, DIODE, HyperSim) datasets, compared to (16%, 18%, 45%, 9%) by ZoeDepth. The code is available at https://github.com/Aradhye2002/EcoDepth.

翻译：在缺乏视差线索的情况下，基于学习的单张图像深度估计（SIDE）模型严重依赖图像中的明暗纹理和上下文信息。尽管这种简洁性具有吸引力，但此类模型需要在难以采集的大规模多样化数据集上进行训练。研究表明，利用预训练基础模型（如CLIP）的嵌入表示可提升若干应用中的零样本迁移能力。受此启发，本文探索使用预训练ViT模型生成的全局图像先验来提供更详细的上下文信息。我们论证，在大规模数据集上预训练的ViT模型所提取的嵌入向量，相比通过生成伪图像描述再基于CLIP文本嵌入的常规方法，能够捕获更多与SIDE相关的关键信息。基于这一思想，我们提出以ViT嵌入为条件的新SIDE扩散框架。所提方案在NYUv2数据集上创下SIDE新标杆：绝对相对误差（Abs Rel）达到0.059（较当前最优方法VPD的0.069提升14%）；在KITTI数据集上平方相对误差（Sq Rel）为0.139（较当前最优方法GEDepth的0.142提升2%）。针对NYUv2训练模型进行零样本迁移时，我们在（Sun-RGBD, iBims1, DIODE, HyperSim）数据集上相较NeWCRFs的平均改进率分别为（20%, 23%, 81%, 25%），而ZoeDepth的对应改进率为（16%, 18%, 45%, 9%）。代码已开源：https://github.com/Aradhye2002/EcoDepth。