Probabilistic Volumetric Fusion for Dense Monocular SLAM

• URL: http://arxiv.org/abs/2210.01276v1
• Date: Mon, 3 Oct 2022 23:53:35 GMT
• Title: Probabilistic Volumetric Fusion for Dense Monocular SLAM
• Authors: Antoni Rosinol, John J. Leonard, Luca Carlone
• Abstract summary: We present a novel method to reconstruct 3D scenes by leveraging deep dense monocular SLAM and fast uncertainty propagation. The proposed approach is able to 3D reconstruct scenes densely, accurately, and in real-time while being robust to extremely noisy depth estimates. We show that our approach achieves 92% better accuracy than directly fusing depths from monocular SLAM, and up to 90% improvements compared to the best competing approach.
• Score: 33.156523309257786
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a novel method to reconstruct 3D scenes from images by leveraging deep dense monocular SLAM and fast uncertainty propagation. The proposed approach is able to 3D reconstruct scenes densely, accurately, and in real-time while being robust to extremely noisy depth estimates coming from dense monocular SLAM. Differently from previous approaches, that either use ad-hoc depth filters, or that estimate the depth uncertainty from RGB-D cameras' sensor models, our probabilistic depth uncertainty derives directly from the information matrix of the underlying bundle adjustment problem in SLAM. We show that the resulting depth uncertainty provides an excellent signal to weight the depth-maps for volumetric fusion. Without our depth uncertainty, the resulting mesh is noisy and with artifacts, while our approach generates an accurate 3D mesh with significantly fewer artifacts. We provide results on the challenging Euroc dataset, and show that our approach achieves 92% better accuracy than directly fusing depths from monocular SLAM, and up to 90% improvements compared to the best competing approach.

Related papers

• Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion [51.69876947593144]
  Existing methods for depth completion operate in tightly constrained settings. Inspired by advances in monocular depth estimation, we reframe depth completion as an image-conditional depth map generation. Marigold-DC builds on a pretrained latent diffusion model for monocular depth estimation and injects the depth observations as test-time guidance.
  arXiv  Detail & Related papers  (2024-12-18T00:06:41Z)
• SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation [17.88798247412388]
  SharpDepth combines the metric accuracy of discriminative depth estimation methods with the fine-grained boundary sharpness typically achieved by generative methods. Our approach bridges these limitations by integrating metric accuracy with detailed boundary preservation, resulting in depth predictions that are both metrically precise and visually sharp.
  arXiv  Detail & Related papers  (2024-11-27T11:07:27Z)
• Uncertainty-guided Optimal Transport in Depth Supervised Sparse-View 3D Gaussian [49.21866794516328]
  3D Gaussian splatting has demonstrated impressive performance in real-time novel view synthesis. Previous approaches have incorporated depth supervision into the training of 3D Gaussians to mitigate overfitting. We introduce a novel method to supervise the depth distribution of 3D Gaussians, utilizing depth priors with integrated uncertainty estimates.
  arXiv  Detail & Related papers  (2024-05-30T03:18:30Z)
• Unveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarios [103.72094710263656]
  This paper presents a novel approach that identifies and integrates dominant cross-modality depth features with a learning-based framework. We propose a novel confidence loss steering a confidence predictor network to yield a confidence map specifying latent potential depth areas. With the resulting confidence map, we propose a multi-modal fusion network that fuses the final depth in an end-to-end manner.
  arXiv  Detail & Related papers  (2024-02-19T04:39:16Z)
• Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matching [0.5067618621449753]
  We propose a non-learning depth completion method for a sparse depth map captured using a light detection and ranging (LiDAR) sensor guided by a pair of stereo images. The proposed method reduced the mean absolute error (MAE) of the depth estimation to 0.65 times and demonstrated approximately twice more accurate estimation in the long range.
  arXiv  Detail & Related papers  (2022-10-04T07:46:56Z)
• Uncertainty Guided Depth Fusion for Spike Camera [49.41822923588663]
  We propose a novel Uncertainty-Guided Depth Fusion (UGDF) framework to fuse predictions of monocular and stereo depth estimation networks for spike camera. Our framework is motivated by the fact that stereo spike depth estimation achieves better results at close range. In order to demonstrate the advantage of spike depth estimation over traditional camera depth estimation, we contribute a spike-depth dataset named CitySpike20K.
  arXiv  Detail & Related papers  (2022-08-26T13:04:01Z)
• Scale-aware direct monocular odometry [4.111899441919165]
  We present a framework for direct monocular odometry based on depth prediction from a deep neural network. Our proposal largely outperforms classic monocular SLAM, being 5 to 9 times more precise, with an accuracy which is closer to that of stereo systems.
  arXiv  Detail & Related papers  (2021-09-21T10:30:15Z)
• Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion [46.97673710849343]
  We address the problem of fusing monocular depth estimation with a conventional multi-view stereo or SLAM. We use a conventional pipeline to produce a sparse 3D point cloud that is fed to a monocular depth estimation network to enhance its performance. We demonstrate the efficacy of our approach by integrating it with a SLAM system built-in on mobile devices.
  arXiv  Detail & Related papers  (2020-12-18T15:19:46Z)
• 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)
• D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry [57.5549733585324]
  D3VO is a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation. We first propose a novel self-supervised monocular depth estimation network trained on stereo videos without any external supervision. We model the photometric uncertainties of pixels on the input images, which improves the depth estimation accuracy.
  arXiv  Detail & Related papers  (2020-03-02T17:47:13Z)

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.