DepthLab: From Partial to Complete

• URL: http://arxiv.org/abs/2412.18153v1
• Date: Tue, 24 Dec 2024 04:16:38 GMT
• Title: DepthLab: From Partial to Complete
• Authors: Zhiheng Liu, Ka Leong Cheng, Qiuyu Wang, Shuzhe Wang, Hao Ouyang, Bin Tan, Kai Zhu, Yujun Shen, Qifeng Chen, Ping Luo,
• Abstract summary: Missing values remain a common challenge for depth data across its wide range of applications. This work bridges this gap with DepthLab, a foundation depth inpainting model powered by image diffusion priors. 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.
• Score: 80.58276388743306
• License:
• Abstract: 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/.

Related papers

• Deep Neural Networks for Accurate Depth Estimation with Latent Space Features [0.0]
  This study introduces a novel depth estimation framework that leverages latent space features within a deep convolutional neural network. The proposed model features dual encoder-decoder architecture, enabling both color-to-depth and depth-to-depth transformations. The framework is thoroughly tested using the NYU Depth V2 dataset, where it sets a new benchmark.
  arXiv  Detail & Related papers  (2025-02-17T13:11:35Z)
• A Two-Stage Masked Autoencoder Based Network for Indoor Depth Completion [10.519644854849098]
  We propose a two-step Transformer-based network for indoor depth completion. Our proposed network achieves the state-of-the-art performance on the Matterport3D dataset. In addition, to validate the importance of the depth completion task, we apply our methods to indoor 3D reconstruction.
  arXiv  Detail & Related papers  (2024-06-14T07:42:27Z)
• InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior [36.23604779569843]
  3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points.
  arXiv  Detail & Related papers  (2024-04-17T17:59:53Z)
• Depth Estimation and Image Restoration by Deep Learning from Defocused Images [2.6599014990168834]
  Two-headed Depth Estimation and Deblurring Network (2HDED:NET) extends a conventional Depth from Defocus (DFD) networks with a deblurring branch that shares the same encoder as the depth branch. The proposed method has been successfully tested on two benchmarks, one for indoor and the other for outdoor scenes: NYU-v2 and Make3D.
  arXiv  Detail & Related papers  (2023-02-21T15:28:42Z)
• On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation [56.97699793236174]
  We study two kinds of robust cross-view consistency in this paper. We exploit the temporal coherence in both depth feature space and 3D voxel space for self-supervised monocular depth estimation. Experimental results on several outdoor benchmarks show that our method outperforms current state-of-the-art techniques.
  arXiv  Detail & Related papers  (2022-09-19T03:46:13Z)
• Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image [91.71077190961688]
  We propose a two-stage framework that first predicts depth up to an unknown scale and shift from a single monocular image. We then exploits 3D point cloud data to predict the depth shift and the camera's focal length that allow us to recover 3D scene shapes. We test our depth model on nine unseen datasets and achieve state-of-the-art performance on zero-shot evaluation.
  arXiv  Detail & Related papers  (2022-08-28T16:20:14Z)
• DynOcc: Learning Single-View Depth from Dynamic Occlusion Cues [37.837552043766166]
  We introduce the first depth dataset DynOcc consisting of dynamic in-the-wild scenes. Our approach leverages the cues in these dynamic scenes to infer depth relationships between points of selected video frames. In total our DynOcc dataset contains 22M depth pairs out of 91K frames from a diverse set of videos.
  arXiv  Detail & Related papers  (2021-03-30T22:17:36Z)
• Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction [87.08227378010874]
  We show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces a simple geometric constraint, we significantly improve the accuracy and robustness of monocular depth estimation. We show state-of-the-art results of learning metric depth on NYU Depth-V2 and KITTI.
  arXiv  Detail & Related papers  (2021-03-07T00:08:21Z)
• Learning Joint 2D-3D Representations for Depth Completion [90.62843376586216]
  We design a simple yet effective neural network block that learns to extract joint 2D and 3D features. Specifically, the block consists of two domain-specific sub-networks that apply 2D convolution on image pixels and continuous convolution on 3D points.
  arXiv  Detail & Related papers  (2020-12-22T22:58:29Z)
• Occlusion-Aware Depth Estimation with Adaptive Normal Constraints [85.44842683936471]
  We present a new learning-based method for multi-frame depth estimation from a color video. Our method outperforms the state-of-the-art in terms of depth estimation accuracy.
  arXiv  Detail & Related papers  (2020-04-02T07:10:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.