Pyramid Deep Fusion Network for Two-Hand Reconstruction from RGB-D Images

• URL: http://arxiv.org/abs/2307.06038v2
• Date: Wed, 10 Apr 2024 03:27:04 GMT
• Title: Pyramid Deep Fusion Network for Two-Hand Reconstruction from RGB-D Images
• Authors: Jinwei Ren, Jianke Zhu,
• Abstract summary: We propose an end-to-end framework for recovering dense meshes for both hands. Our framework employs ResNet50 and PointNet++ to derive features from RGB and point cloud. We also introduce a novel pyramid deep fusion network (PDFNet) to aggregate features at different scales.
• Score: 11.100398985633754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurately recovering the dense 3D mesh of both hands from monocular images poses considerable challenges due to occlusions and projection ambiguity. Most of the existing methods extract features from color images to estimate the root-aligned hand meshes, which neglect the crucial depth and scale information in the real world. Given the noisy sensor measurements with limited resolution, depth-based methods predict 3D keypoints rather than a dense mesh. These limitations motivate us to take advantage of these two complementary inputs to acquire dense hand meshes on a real-world scale. In this work, we propose an end-to-end framework for recovering dense meshes for both hands, which employ single-view RGB-D image pairs as input. The primary challenge lies in effectively utilizing two different input modalities to mitigate the blurring effects in RGB images and noises in depth images. Instead of directly treating depth maps as additional channels for RGB images, we encode the depth information into the unordered point cloud to preserve more geometric details. Specifically, our framework employs ResNet50 and PointNet++ to derive features from RGB and point cloud, respectively. Additionally, we introduce a novel pyramid deep fusion network (PDFNet) to aggregate features at different scales, which demonstrates superior efficacy compared to previous fusion strategies. Furthermore, we employ a GCN-based decoder to process the fused features and recover the corresponding 3D pose and dense mesh. Through comprehensive ablation experiments, we have not only demonstrated the effectiveness of our proposed fusion algorithm but also outperformed the state-of-the-art approaches on publicly available datasets. To reproduce the results, we will make our source code and models publicly available at {https://github.com/zijinxuxu/PDFNet}.

Related papers

• AGG-Net: Attention Guided Gated-convolutional Network for Depth Image Completion [1.8820731605557168]
  We propose a new model for depth image completion based on the Attention Guided Gated-convolutional Network (AGG-Net) In the encoding stage, an Attention Guided Gated-Convolution (AG-GConv) module is proposed to realize the fusion of depth and color features at different scales. In the decoding stage, an Attention Guided Skip Connection (AG-SC) module is presented to avoid introducing too many depth-irrelevant features to the reconstruction.
  arXiv  Detail & Related papers  (2023-09-04T14:16:08Z)
• VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusion [62.24001258298076]
  VPFNet is a new architecture that cleverly aligns and aggregates the point cloud and image data at the virtual' points. Our VPFNet achieves 83.21% moderate 3D AP and 91.86% moderate BEV AP on the KITTI test set, ranking the 1st since May 21th, 2021.
  arXiv  Detail & Related papers  (2021-11-29T08:51:20Z)
• VR3Dense: Voxel Representation Learning for 3D Object Detection and Monocular Dense Depth Reconstruction [0.951828574518325]
  We introduce a method for jointly training 3D object detection and monocular dense depth reconstruction neural networks. It takes as inputs, a LiDAR point-cloud, and a single RGB image during inference and produces object pose predictions as well as a densely reconstructed depth map. While our object detection is trained in a supervised manner, the depth prediction network is trained with both self-supervised and supervised loss functions.
  arXiv  Detail & Related papers  (2021-04-13T04:25:54Z)
• FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation [54.666329929930455]
  We present FFB6D, a Bidirectional fusion network designed for 6D pose estimation from a single RGBD image. We learn to combine appearance and geometry information for representation learning as well as output representation selection. Our method outperforms the state-of-the-art by large margins on several benchmarks.
  arXiv  Detail & Related papers  (2021-03-03T08:07:29Z)
• Learning Joint 2D-3D Representations for Depth Completion [90.62843376586216]
  We design a simple yet effective neural network block that learns to extract joint 2D and 3D features. Specifically, the block consists of two domain-specific sub-networks that apply 2D convolution on image pixels and continuous convolution on 3D points.
  arXiv  Detail & Related papers  (2020-12-22T22:58:29Z)
• Adaptive Context-Aware Multi-Modal Network for Depth Completion [107.15344488719322]
  We propose to adopt the graph propagation to capture the observed spatial contexts. We then apply the attention mechanism on the propagation, which encourages the network to model the contextual information adaptively. Finally, we introduce the symmetric gated fusion strategy to exploit the extracted multi-modal features effectively. Our model, named Adaptive Context-Aware Multi-Modal Network (ACMNet), achieves the state-of-the-art performance on two benchmarks.
  arXiv  Detail & Related papers  (2020-08-25T06:00:06Z)
• Cross-Modality 3D Object Detection [63.29935886648709]
  We present a novel two-stage multi-modal fusion network for 3D object detection. The whole architecture facilitates two-stage fusion. Our experiments on the KITTI dataset show that the proposed multi-stage fusion helps the network to learn better representations.
  arXiv  Detail & Related papers  (2020-08-16T11:01:20Z)
• A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection [89.88222217065858]
  We design a single stream network to use the depth map to guide early fusion and middle fusion between RGB and depth. This model is 55.5% lighter than the current lightest model and runs at a real-time speed of 32 FPS when processing a $384 times 384$ image.
  arXiv  Detail & Related papers  (2020-07-14T04:40:14Z)
• 3dDepthNet: Point Cloud Guided Depth Completion Network for Sparse Depth and Single Color Image [42.13930269841654]
  Our network offers a novel 3D-to-2D coarse-to-fine dual densification design that is both accurate and lightweight. Experiments on the KITTI dataset show our network achieves state-of-art accuracy while being more efficient.
  arXiv  Detail & Related papers  (2020-03-20T10:19:32Z)
• 3D Gated Recurrent Fusion for Semantic Scene Completion [32.86736222106503]
  This paper tackles the problem of data fusion in the semantic scene completion (SSC) task. We propose a 3D gated recurrent fusion network (GRFNet), which learns to adaptively select and fuse the relevant information from depth and RGB. Experiments on two benchmark datasets demonstrate the superior performance and the effectiveness of the proposed GRFNet for data fusion in SSC.
  arXiv  Detail & Related papers  (2020-02-17T21:45:43Z)

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.