AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation
- URL: http://arxiv.org/abs/2310.09739v3
- Date: Sat, 20 Jul 2024 01:28:16 GMT
- Title: AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation
- Authors: Yangchao Wu, Tian Yu Liu, Hyoungseob Park, Stefano Soatto, Dong Lao, Alex Wong,
- Abstract summary: We propose a method that unlocks a wide range of previously-infeasible geometric augmentations for unsupervised depth computation and estimation.
This is achieved by reversing, or undo''-ing, geometric transformations to the coordinates of the output depth, warping the depth map back to the original reference frame.
- Score: 51.143540967290114
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Unsupervised depth completion and estimation methods are trained by minimizing reconstruction error. Block artifacts from resampling, intensity saturation, and occlusions are amongst the many undesirable by-products of common data augmentation schemes that affect image reconstruction quality, and thus the training signal. Hence, typical augmentations on images viewed as essential to training pipelines in other vision tasks have seen limited use beyond small image intensity changes and flipping. The sparse depth modality in depth completion have seen even less use as intensity transformations alter the scale of the 3D scene, and geometric transformations may decimate the sparse points during resampling. We propose a method that unlocks a wide range of previously-infeasible geometric augmentations for unsupervised depth completion and estimation. This is achieved by reversing, or ``undo''-ing, geometric transformations to the coordinates of the output depth, warping the depth map back to the original reference frame. This enables computing the reconstruction losses using the original images and sparse depth maps, eliminating the pitfalls of naive loss computation on the augmented inputs and allowing us to scale up augmentations to boost performance. We demonstrate our method on indoor (VOID) and outdoor (KITTI) datasets, where we consistently improve upon recent methods across both datasets as well as generalization to four other datasets. Code available at: https://github.com/alexklwong/augundo.
Related papers
- Temporal Lidar Depth Completion [0.08192907805418582]
We show how a state-of-the-art method PENet can be modified to benefit from recurrency.
Our algorithm achieves state-of-the-art results on the KITTI depth completion dataset.
arXiv Detail & Related papers (2024-06-17T08:25:31Z) - Robust Geometry-Preserving Depth Estimation Using Differentiable
Rendering [93.94371335579321]
We propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations.
Comprehensive experiments underscore our framework's superior generalization capabilities.
Our innovative loss functions empower the model to autonomously recover domain-specific scale-and-shift coefficients.
arXiv Detail & Related papers (2023-09-18T12:36:39Z) - 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) - Deep Generalized Unfolding Networks for Image Restoration [16.943609020362395]
We propose a Deep Generalized Unfolding Network (DGUNet) for image restoration.
We integrate a gradient estimation strategy into the gradient descent step of the Proximal Gradient Descent (PGD) algorithm.
Our method is superior in terms of state-of-the-art performance, interpretability, and generalizability.
arXiv Detail & Related papers (2022-04-28T08:39:39Z) - 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 to Recover 3D Scene Shape from a Single Image [98.20106822614392]
We propose a two-stage framework that first predicts depth up to an unknown scale and shift from a single monocular image.
We then use 3D point cloud encoders to predict the missing depth shift and focal length that allow us to recover a realistic 3D scene shape.
arXiv Detail & Related papers (2020-12-17T02:35:13Z) - Towards Better Generalization: Joint Depth-Pose Learning without PoseNet [36.414471128890284]
We tackle the essential problem of scale inconsistency for self-supervised joint depth-pose learning.
Most existing methods assume that a consistent scale of depth and pose can be learned across all input samples.
We propose a novel system that explicitly disentangles scale from the network estimation.
arXiv Detail & Related papers (2020-04-03T00:28:09Z) - 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.