Decomposition of Neural Discrete Representations for Large-Scale 3D Mapping

• URL: http://arxiv.org/abs/2407.15554v1
• Date: Mon, 22 Jul 2024 11:32:33 GMT
• Title: Decomposition of Neural Discrete Representations for Large-Scale 3D Mapping
• Authors: Minseong Park, Suhan Woo, Euntai Kim,
• Abstract summary: We introduce Decomposition-based Neural Mapping (DNMap) DNMap is a storage-efficient large-scale 3D mapping method. We learn low-resolution continuous embeddings that require tiny storage space.
• Score: 15.085191496726967
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning efficient representations of local features is a key challenge in feature volume-based 3D neural mapping, especially in large-scale environments. In this paper, we introduce Decomposition-based Neural Mapping (DNMap), a storage-efficient large-scale 3D mapping method that employs a discrete representation based on a decomposition strategy. This decomposition strategy aims to efficiently capture repetitive and representative patterns of shapes by decomposing each discrete embedding into component vectors that are shared across the embedding space. Our DNMap optimizes a set of component vectors, rather than entire discrete embeddings, and learns composition rather than indexing the discrete embeddings. Furthermore, to complement the mapping quality, we additionally learn low-resolution continuous embeddings that require tiny storage space. By combining these representations with a shallow neural network and an efficient octree-based feature volume, our DNMap successfully approximates signed distance functions and compresses the feature volume while preserving mapping quality. Our source code is available at https://github.com/minseong-p/dnmap.

Related papers

• OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mapping [19.176488228253483]
  3DGS has recently demonstrated promising advancements in RGB-D online dense mapping. Existing methods excessively rely on per-pixel depth cues to perform map densification. We introduce OG-Mapping, which leverages the robust scene structural representation capability of sparse octrees.
  arXiv  Detail & Related papers  (2024-08-30T12:01:59Z)
• Representing 3D sparse map points and lines for camera relocalization [1.2974519529978974]
  We show how a lightweight neural network can learn to represent both 3D point and line features. In tests, our method secures a significant lead, marking the most considerable enhancement over state-of-the-art learning-based methodologies.
  arXiv  Detail & Related papers  (2024-02-28T03:07:05Z)
• SeMLaPS: Real-time Semantic Mapping with Latent Prior Networks and Quasi-Planar Segmentation [53.83313235792596]
  We present a new methodology for real-time semantic mapping from RGB-D sequences. It combines a 2D neural network and a 3D network based on a SLAM system with 3D occupancy mapping. Our system achieves state-of-the-art semantic mapping quality within 2D-3D networks-based systems.
  arXiv  Detail & Related papers  (2023-06-28T22:36:44Z)
• 3D Small Object Detection with Dynamic Spatial Pruning [62.72638845817799]
  We propose an efficient feature pruning strategy for 3D small object detection. We present a multi-level 3D detector named DSPDet3D which benefits from high spatial resolution. It takes less than 2s to directly process a whole building consisting of more than 4500k points while detecting out almost all objects.
  arXiv  Detail & Related papers  (2023-05-05T17:57:04Z)
• Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis [66.49788145564004]
  We present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology. Our methods perform favorably against the current state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-12-17T15:05:25Z)
• SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations [37.733802382489515]
  This paper addresses the problems of achieving large-scale 3D reconstructions with implicit representations using 3D LiDAR measurements. We learn and store implicit features through an octree-based hierarchical structure, which is sparse and sparse. Our experiments show that our 3D reconstructions are more accurate, complete, and memory-efficient than current state-of-the-art 3D mapping methods.
  arXiv  Detail & Related papers  (2022-10-05T14:38:49Z)
• HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection [39.64891219500416]
  3D object detection methods exploit either voxel-based or point-based features to represent 3D objects in a scene. We introduce in this paper a novel single-stage 3D detection method having the merit of both voxel-based and point-based features.
  arXiv  Detail & Related papers  (2021-04-02T06:34:49Z)
• Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes [77.6741486264257]
  We introduce an efficient neural representation that, for the first time, enables real-time rendering of high-fidelity neural SDFs. We show that our representation is 2-3 orders of magnitude more efficient in terms of rendering speed compared to previous works.
  arXiv  Detail & Related papers  (2021-01-26T18:50:22Z)
• DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation [7.2531609092488445]
  We develop a convolutional neural network architecture which aggregates feature maps at different semantic levels for image representations. Second, our model is trained end-to-end without pixel-level annotation other than positive and negative GPS-tagged image pairs. Third, our method is computationally efficient as our architecture has shared features and parameters during computation.
  arXiv  Detail & Related papers  (2020-12-04T02:16:47Z)
• Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
  Representation learning for 3D meshes is important in many computer vision and graphics applications. We propose a local structure-aware anisotropic convolutional operation (LSA-Conv) Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-21T13:40:03Z)
• Convolutional Occupancy Networks [88.48287716452002]
  We propose Convolutional Occupancy Networks, a more flexible implicit representation for detailed reconstruction of objects and 3D scenes. By combining convolutional encoders with implicit occupancy decoders, our model incorporates inductive biases, enabling structured reasoning in 3D space. We empirically find that our method enables the fine-grained implicit 3D reconstruction of single objects, scales to large indoor scenes, and generalizes well from synthetic to real data.
  arXiv  Detail & Related papers  (2020-03-10T10:17:07Z)

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.