FS-Depth: Focal-and-Scale Depth Estimation from a Single Image in Unseen Indoor Scene

• URL: http://arxiv.org/abs/2307.14624v1
• Date: Thu, 27 Jul 2023 04:49:36 GMT
• Title: FS-Depth: Focal-and-Scale Depth Estimation from a Single Image in Unseen Indoor Scene
• Authors: Chengrui Wei, Meng Yang, Lei He, Nanning Zheng
• Abstract summary: It has long been an ill-posed problem to predict absolute depth maps from single images in real (unseen) indoor scenes. We develop a focal-and-scale depth estimation model to well learn absolute depth maps from single images in unseen indoor scenes.
• Score: 57.26600120397529
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It has long been an ill-posed problem to predict absolute depth maps from single images in real (unseen) indoor scenes. We observe that it is essentially due to not only the scale-ambiguous problem but also the focal-ambiguous problem that decreases the generalization ability of monocular depth estimation. That is, images may be captured by cameras of different focal lengths in scenes of different scales. In this paper, we develop a focal-and-scale depth estimation model to well learn absolute depth maps from single images in unseen indoor scenes. First, a relative depth estimation network is adopted to learn relative depths from single images with diverse scales/semantics. Second, multi-scale features are generated by mapping a single focal length value to focal length features and concatenating them with intermediate features of different scales in relative depth estimation. Finally, relative depths and multi-scale features are jointly fed into an absolute depth estimation network. In addition, a new pipeline is developed to augment the diversity of focal lengths of public datasets, which are often captured with cameras of the same or similar focal lengths. Our model is trained on augmented NYUDv2 and tested on three unseen datasets. Our model considerably improves the generalization ability of depth estimation by 41%/13% (RMSE) with/without data augmentation compared with five recent SOTAs and well alleviates the deformation problem in 3D reconstruction. Notably, our model well maintains the accuracy of depth estimation on original NYUDv2.

Related papers

• Robust and Flexible Omnidirectional Depth Estimation with Multiple 360° Cameras [8.850391039025077]
  We use geometric constraints and redundant information of multiple 360-degree cameras to achieve robust and flexible omnidirectional depth estimation. Our two algorithms achieve state-of-the-art performance, accurately predicting depth maps even when provided with soiled panorama inputs.
  arXiv  Detail & Related papers  (2024-09-23T07:31:48Z)
• ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation [62.600382533322325]
  We propose a novel monocular depth estimation method called ScaleDepth. Our method decomposes metric depth into scene scale and relative depth, and predicts them through a semantic-aware scale prediction module. Our method achieves metric depth estimation for both indoor and outdoor scenes in a unified framework.
  arXiv  Detail & Related papers  (2024-07-11T05:11:56Z)
• Blur aware metric depth estimation with multi-focus plenoptic cameras [8.508198765617196]
  We present a new metric depth estimation algorithm using only raw images from a multi-focus plenoptic camera. The proposed approach is especially suited for the multi-focus configuration where several micro-lenses with different focal lengths are used.
  arXiv  Detail & Related papers  (2023-08-08T13:38:50Z)
• Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation [75.99435808648784]
  We propose a novel multi-camera collaborative depth prediction method. It does not require large overlapping areas while maintaining structure consistency between cameras. Experimental results on DDAD and NuScenes datasets demonstrate the superior performance of our method.
  arXiv  Detail & Related papers  (2022-10-05T03:44:34Z)
• 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)
• Depth Refinement for Improved Stereo Reconstruction [13.941756438712382]
  Current techniques for depth estimation from stereoscopic images still suffer from a built-in drawback. A simple analysis reveals that the depth error is quadratically proportional to the object's distance. We propose a simple but effective method that uses a refinement network for depth estimation.
  arXiv  Detail & Related papers  (2021-12-15T12:21:08Z)
• 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)
• Depth Completion Using a View-constrained Deep Prior [73.21559000917554]
  Recent work has shown that the structure of convolutional neural networks (CNNs) induces a strong prior that favors natural images. This prior, known as a deep image prior (DIP), is an effective regularizer in inverse problems such as image denoising and inpainting. We extend the concept of the DIP to depth images. Given color images and noisy and incomplete target depth maps, we reconstruct a depth map restored by virtue of using the CNN network structure as a prior.
  arXiv  Detail & Related papers  (2020-01-21T21:56:01Z)

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.