PF-Net: Point Fractal Network for 3D Point Cloud Completion

GASCN: Graph Attention Shape Completion Network

Shape completion, the problem of inferring the complete geometry of an object given a partial point cloud, is an important problem in robotics and computer vision. This paper proposes the Graph Attention Shape Completion Network (GASCN), a novel neural network model that solves this problem. This model combines a graph-based model for encoding local point cloud information with an MLP-based architecture for encoding global information. For each completed point, our model infers the normal and extent of the local surface patch which is used to produce dense yet precise shape completions. We rep…

ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion

We tackle the problem of object completion from point clouds and propose a novel point cloud completion network employing an Asymmetrical Siamese Feature Matching strategy, termed as ASFM-Net. Specifically, the Siamese auto-encoder neural network is adopted to map the partial and complete input point cloud into a shared latent space, which can capture detailed shape prior. Then we design an iterative refinement unit to generate complete shapes with fine-grained details by integrating prior information. Experiments are conducted on the PCN dataset and the Completion3D benchmark, demonstrating t…

利用一致性损失提升点云补全网络性能

Enhancing Performance of Point Cloud Completion Networks with Consistency Loss

针对点云补全中一对多映射导致的优化干扰问题，提出补全一致性损失，在不改网络结构、不影响推理速度的前提下提升现有网络补全精度，在MVP数据集上达到SOTA。

FractalNet: Ultra-Deep Neural Networks without Residuals

We introduce a design strategy for neural network macro-architecture based on self-similarity. Repeated application of a simple expansion rule generates deep networks whose structural layouts are precisely truncated fractals. These networks contain interacting subpaths of different lengths, but do not include any pass-through or residual connections; every internal signal is transformed by a filter and nonlinearity before being seen by subsequent layers. In experiments, fractal networks match the excellent performance of standard residual networks on both CIFAR and ImageNet classification task…

FractalPINN-Flow：一种受分形启发的网络用于无监督光流估计与总变分正则化

FractalPINN-Flow: A Fractal-Inspired Network for Unsupervised Optical Flow Estimation with Total Variation Regularization

本文提出FractalPINN-Flow，一种无监督深度学习框架，通过连续灰度帧直接学习光流，无需真实数据。基于分形几何和自相似性设计的分形变形网络，结合总变分正则化，实现高精度、平滑且边缘保留的光流估计。

SoFAr: Shortcut-based Fractal Architectures for Binary Convolutional Neural Networks

Binary Convolutional Neural Networks (BCNNs) can significantly improve the efficiency of Deep Convolutional Neural Networks (DCNNs) for their deployment on resource-constrained platforms, such as mobile and embedded systems. However, the accuracy degradation of BCNNs is still considerable compared with their full precision counterpart, impeding their practical deployment. Because of the inevitable binarization error in the forward propagation and gradient mismatch problem in the backward propagation, it is nontrivial to train BCNNs to achieve satisfactory accuracy. To ease the difficulty of tr…