RocNet: Recursive Octree Network for Efficient 3D Deep Representation

• URL: http://arxiv.org/abs/2008.03875v1
• Date: Mon, 10 Aug 2020 03:02:10 GMT
• Title: RocNet: Recursive Octree Network for Efficient 3D Deep Representation
• Authors: Juncheng Liu, Steven Mills, Brendan McCane
• Abstract summary: Our network compresses a voxel grid of any size down to a very small latent space in an autoencoder-like network. We show results for compressing 32, 64 and 128 grids down to just 80 floats in the latent space.
• Score: 3.7298568326039026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a deep recursive octree network for the compression of 3D voxel data. Our network compresses a voxel grid of any size down to a very small latent space in an autoencoder-like network. We show results for compressing 32, 64 and 128 grids down to just 80 floats in the latent space. We demonstrate the effectiveness and efficiency of our proposed method on several publicly available datasets with three experiments: 3D shape classification, 3D shape reconstruction, and shape generation. Experimental results show that our algorithm maintains accuracy while consuming less memory with shorter training times compared to existing methods, especially in 3D reconstruction tasks.

Related papers

• Fast Sparse 3D Convolution Network with VDB [2.834312349049142]
  We proposed a new Convolution Neural Network implementation optimized for sparse 3D data inference. This implementation uses NanoVDB as the data structure to store the sparse tensor. We demonstrate that this architecture is around 20 times faster than the state-of-the-art dense CNN model on a high-resolution 3D object classification network.
  arXiv  Detail & Related papers  (2023-11-05T20:43:46Z)
• 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)
• ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapes [32.267066838654834]
  We present a novel implicit representation to efficiently and accurately encode large datasets of complex 3D shapes. Our implicit Recursive Octree Auto-Decoder (ROAD) learns a hierarchically structured latent space enabling state-of-the-art reconstruction results at a compression ratio above 99%.
  arXiv  Detail & Related papers  (2022-12-12T19:09:47Z)
• Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations [21.59311861556396]
  Our method encodes the volumetric field of a 3D shape with an adaptive feature volume organized by an octree. An encoder-decoder network is designed to learn the adaptive feature volume based on the graph convolutions over the dual graph of octree nodes. Our method effectively encodes shape details, enables fast 3D shape reconstruction, and exhibits good generality for modeling 3D shapes out of training categories.
  arXiv  Detail & Related papers  (2022-05-05T17:56:34Z)
• Mesh Convolution with Continuous Filters for 3D Surface Parsing [101.25796935464648]
  We propose a series of modular operations for effective geometric feature learning from 3D triangle meshes. Our mesh convolutions exploit spherical harmonics as orthonormal bases to create continuous convolutional filters. We further contribute a novel hierarchical neural network for perceptual parsing of 3D surfaces, named PicassoNet++.
  arXiv  Detail & Related papers  (2021-12-03T09:16:49Z)
• Putting 3D Spatially Sparse Networks on a Diet [21.881294733075393]
  We propose a compact weight-sparse and spatially sparse 3D convnet (WS3-ConvNet) for semantic segmentation and instance segmentation. We employ various network pruning strategies to find compact networks and show our WS3-ConvNet achieves minimal loss in performance (2-15% drop) with orders-of-15% smaller number of parameters (1/100 compression rate) Finally, we systematically analyze the compression patterns of WS3-ConvNet and show interesting emerging sparsity patterns common in our compressed networks to further speed up inference.
  arXiv  Detail & Related papers  (2021-12-02T15:20:15Z)
• R2U3D: Recurrent Residual 3D U-Net for Lung Segmentation [17.343802171952195]
  We propose a novel model, namely, Recurrent Residual 3D U-Net (R2U3D), for the 3D lung segmentation task. In particular, the proposed model integrates 3D convolution into the Recurrent Residual Neural Network based on U-Net. The proposed R2U3D network is trained on the publicly available dataset LUNA16 and it achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-05-05T19:17:14Z)
• 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)
• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net [93.51773847125014]
  We propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor. Our approach performs 3D convolutions across space and time over a bird's eye view representation of the 3D world.
  arXiv  Detail & Related papers  (2020-12-22T22:43:35Z)
• OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression [77.8842824702423]
  We present a novel deep compression algorithm to reduce the memory footprint of LiDAR point clouds. Our method exploits the sparsity and structural redundancy between points to reduce the memory footprint. Our algorithm can be used to reduce the onboard and offboard storage of LiDAR points for applications such as self-driving cars.
  arXiv  Detail & Related papers  (2020-05-14T17:48:49Z)
• Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion [53.885984328273686]
  Implicit Feature Networks (IF-Nets) deliver continuous outputs, can handle multiple topologies, and complete shapes for missing or sparse input data. IF-Nets clearly outperform prior work in 3D object reconstruction in ShapeNet, and obtain significantly more accurate 3D human reconstructions.
  arXiv  Detail & Related papers  (2020-03-03T11:14:29Z)

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.