深度实验室：从部分到完整

摘要

在深度数据的各种应用中，缺失值仍然是一个常见挑战，这源于诸如数据采集不完整和视角改变等各种原因。本研究通过DepthLab来填补这一空白，这是一个基于图像扩散先验的基础深度修复模型。我们的模型具有两个显著优势：(1) 它表现出对深度不足区域的弹性，可为连续区域和孤立点提供可靠的补全，以及 (2) 在填补缺失值时，它能够忠实地保持与已知深度的尺度一致性。利用这些优势，我们的方法在各种下游任务中证明了其价值，包括3D场景修复、文本到3D场景生成、使用DUST3R进行稀疏视图重建以及LiDAR深度补全，在数值性能和视觉质量方面均超过当前解决方案。我们的项目页面和源代码可在https://johanan528.github.io/depthlab_web/ 上找到。

English

Missing values remain a common challenge for depth data across its wide range of applications, stemming from various causes like incomplete data acquisition and perspective alteration. This work bridges this gap with DepthLab, a foundation depth inpainting model powered by image diffusion priors. Our model features two notable strengths: (1) it demonstrates resilience to depth-deficient regions, providing reliable completion for both continuous areas and isolated points, and (2) it faithfully preserves scale consistency with the conditioned known depth when filling in missing values. Drawing on these advantages, our approach proves its worth in various downstream tasks, including 3D scene inpainting, text-to-3D scene generation, sparse-view reconstruction with DUST3R, and LiDAR depth completion, exceeding current solutions in both numerical performance and visual quality. Our project page with source code is available at https://johanan528.github.io/depthlab_web/.

深度实验室：从部分到完整

DepthLab: From Partial to Complete

摘要

Summary

Support