Kick Back & Relax++：利用 SlowTV 与 CribsTV 扩展超越真实深度标注的规模
Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV
AI总结：
本文构建包含200万帧、场景多样的 SlowTV 与 CribsTV 数据集，并结合相机内参学习、强增强和 transformer 架构等改进，显著提升自监督单目深度估计的零样本泛化能力。
摘要：
自监督学习是释放通用计算机视觉系统潜力的关键。通过消除对真实标注的依赖，它能够扩展到更大的数据量。遗憾的是，自监督单目深度估计（SS-MDE）一直受到训练数据多样性不足的限制。现有数据集几乎只关注人口稠密城市中的城市驾驶场景，导致训练出的模型无法泛化到该领域之外。为解决这些局限，本文提出了两个新数据集：SlowTV 和 CribsTV。它们是从公开可用的 YouTube 视频中整理得到的大规模数据集，共包含 200 万个训练帧。这些数据集提供了极其多样的环境，从积雪森林到沿海公路、豪华宅邸，甚至水下珊瑚礁。我们利用这些数据集应对具有挑战性的零样本泛化任务，其表现优于所有现有 SS-MDE 方法，甚至超过一些最先进的监督方法。我们模型的泛化能力还通过一系列组件和贡献得到进一步增强：1）学习相机内参；2）针对宽高比变化的更强增强机制；3）支撑帧随机化；4）灵活的运动估计；5）现代的基于 transformer 的架构。我们通过大量消融实验证明了每个组件的有效性。为促进未来研究发展，我们在 https://github.com/jspenmar/slowtv_monodepth 向公众公开数据集、代码和预训练模型。
英文摘要：
Self-supervised learning is the key to unlocking generic computer vision systems. By eliminating the reliance on ground-truth annotations, it allows scaling to much larger data quantities. Unfortunately, self-supervised monocular depth estimation (SS-MDE) has been limited by the absence of diverse training data. Existing datasets have focused exclusively on urban driving in densely populated cities, resulting in models that fail to generalize beyond this domain. To address these limitations, this paper proposes two novel datasets: SlowTV and CribsTV. These are large-scale datasets curated from publicly available YouTube videos, containing a total of 2M training frames. They offer an incredibly diverse set of environments, ranging from snowy forests to coastal roads, luxury mansions and even underwater coral reefs. We leverage these datasets to tackle the challenging task of zero-shot generalization, outperforming every existing SS-MDE approach and even some state-of-the-art supervised methods. The generalization capabilities of our models are further enhanced by a range of components and contributions: 1) learning the camera intrinsics, 2) a stronger augmentation regime targeting aspect ratio changes, 3) support frame randomization, 4) flexible motion estimation, 5) a modern transformer-based architecture. We demonstrate the effectiveness of each component in extensive ablation experiments. To facilitate the development of future research, we make the datasets, code and pretrained models available to the public at https://github.com/jspenmar/slowtv_monodepth.
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。
