Efficient Surfel Fusion Using Normalised Information Distance

• URL: http://arxiv.org/abs/2108.05163v1
• Date: Wed, 11 Aug 2021 11:28:31 GMT
• Title: Efficient Surfel Fusion Using Normalised Information Distance
• Authors: Louis Gallagher and John B. McDonald
• Abstract summary: We present a new technique that achieves a significant reduction in the quantity of measurements required for a fusion based dense 3D mapping system. This is achieved through the use of a Normalised Information Distance metric. We report results of the technique's scalability and the accuracy of the resultant maps by applying it to both the ICL-NUIM and TUM RGB-D datasets.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a new technique that achieves a significant reduction in the quantity of measurements required for a fusion based dense 3D mapping system to converge to an accurate, de-noised surface reconstruction. This is achieved through the use of a Normalised Information Distance metric, that computes the novelty of the information contained in each incoming frame with respect to the reconstruction, and avoids fusing those frames that exceed a redundancy threshold. This provides a principled approach for opitmising the trade-off between surface reconstruction accuracy and the computational cost of processing frames. The technique builds upon the ElasticFusion (EF) algorithm where we report results of the technique's scalability and the accuracy of the resultant maps by applying it to both the ICL-NUIM and TUM RGB-D datasets. These results demonstrate the capabilities of the approach in performing accurate surface reconstructions whilst utilising a fraction of the frames when compared to the original EF algorithm.

Related papers

• Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis [11.236094544193605]
  Conventional geometry-based SLAM systems lack dense 3D reconstruction capabilities. We propose a real-time RGB-D SLAM system that incorporates a novel view synthesis technique, 3D Gaussian Splatting.
  arXiv  Detail & Related papers  (2024-08-10T21:23:08Z)
• Q-SLAM: Quadric Representations for Monocular SLAM [85.82697759049388]
  We reimagine volumetric representations through the lens of quadrics. We use quadric assumption to rectify noisy depth estimations from RGB inputs. We introduce a novel quadric-decomposed transformer to aggregate information across quadrics.
  arXiv  Detail & Related papers  (2024-03-12T23:27:30Z)
• GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting [51.96353586773191]
  We introduce textbfGS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping system. Our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets.
  arXiv  Detail & Related papers  (2023-11-20T12:08:23Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids [84.90863397388776]
  We propose to directly use signed distance function (SDF) in sparse voxel block grids for fast and accurate scene reconstruction without distances. Our globally sparse and locally dense data structure exploits surfaces' spatial sparsity, enables cache-friendly queries, and allows direct extensions to multi-modal data. Experiments show that our approach is 10x faster in training and 100x faster in rendering while achieving comparable accuracy to state-of-the-art neural implicit methods.
  arXiv  Detail & Related papers  (2023-05-22T16:50:19Z)
• SST-ReversibleNet: Reversible-prior-based Spectral-Spatial Transformer for Efficient Hyperspectral Image Reconstruction [15.233185887461826]
  A novel framework called the reversible-prior-based method is proposed. ReversibleNet significantly outperforms state-of-the-art methods on simulated and real HSI datasets.
  arXiv  Detail & Related papers  (2023-05-06T14:01:02Z)
• InFusionSurf: Refining Neural RGB-D Surface Reconstruction Using Per-Frame Intrinsic Refinement and TSDF Fusion Prior Learning [4.406340836209291]
  We introduce InFusionSurf, an innovative enhancement for neural radiance field (NeRF) frameworks in 3D surface reconstruction using RGB-D video frames. InFusionSurf addresses camera motion-induced blurs in each depth frame through a per-frame intrinsic refinement scheme. It incorporates the truncated signed distance field (TSDF) Fusion, a classical real-time 3D surface reconstruction method, as a pretraining tool.
  arXiv  Detail & Related papers  (2023-03-08T10:57:14Z)
• A Probabilistic Deep Image Prior for Computational Tomography [0.19573380763700707]
  Existing deep-learning based tomographic image reconstruction methods do not provide accurate estimates of reconstruction uncertainty. We construct a Bayesian prior for tomographic reconstruction, which combines the classical total variation (TV) regulariser with the modern deep image prior (DIP) For the inference, we develop an approach based on the linearised Laplace method, which is scalable to high-dimensional settings.
  arXiv  Detail & Related papers  (2022-02-28T14:47:14Z)
• Consistent and symmetry preserving data-driven interface reconstruction for the level-set method [0.0]
  We focus on interface reconstruction (IR) in the level-set method, i.e. the computation of the volume fraction and apertures. The proposed approach improves accuracy for coarsely resolved interfaces and recovers the conventional IR for high resolutions. We provide details of floating point symmetric implementation and computational efficiency.
  arXiv  Detail & Related papers  (2021-04-23T13:21:10Z)
• Riggable 3D Face Reconstruction via In-Network Optimization [58.016067611038046]
  This paper presents a method for riggable 3D face reconstruction from monocular images. It jointly estimates a personalized face rig and per-image parameters including expressions, poses, and illuminations. Experiments demonstrate that our method achieves SOTA reconstruction accuracy, reasonable robustness and generalization ability.
  arXiv  Detail & Related papers  (2021-04-08T03:53:20Z)
• SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion [86.77318031029404]
  We propose a framework that performs scene reconstruction and semantic scene completion jointly in an incremental and real-time manner. Our framework relies on a novel neural architecture designed to process occupancy maps and leverages voxel states to accurately and efficiently fuse semantic completion with the 3D global model.
  arXiv  Detail & Related papers  (2020-10-26T15:31:52Z)

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.