Human Pose Estimation on Privacy-Preserving Low-Resolution Depth Images

• URL: http://arxiv.org/abs/2007.08340v2
• Date: Fri, 20 Aug 2021 10:48:22 GMT
• Title: Human Pose Estimation on Privacy-Preserving Low-Resolution Depth Images
• Authors: Vinkle Srivastav, Afshin Gangi, Nicolas Padoy
• Abstract summary: Human pose estimation (HPE) is a key building block for developing AI-based context-aware systems inside the operating room (OR) Being able to solely use low-resolution privacy-preserving images would address these concerns. We propose an end-to-end solution that integrates a multi-scale super-resolution network with a 2D human pose estimation network.
• Score: 2.8802646903517957
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Human pose estimation (HPE) is a key building block for developing AI-based context-aware systems inside the operating room (OR). The 24/7 use of images coming from cameras mounted on the OR ceiling can however raise concerns for privacy, even in the case of depth images captured by RGB-D sensors. Being able to solely use low-resolution privacy-preserving images would address these concerns and help scale up the computer-assisted approaches that rely on such data to a larger number of ORs. In this paper, we introduce the problem of HPE on low-resolution depth images and propose an end-to-end solution that integrates a multi-scale super-resolution network with a 2D human pose estimation network. By exploiting intermediate feature-maps generated at different super-resolution, our approach achieves body pose results on low-resolution images (of size 64x48) that are on par with those of an approach trained and tested on full resolution images (of size 640x480).

Related papers

• Visual Place Recognition with Low-Resolution Images [17.847661026367767]
  We analyse the effects of image resolution on the accuracy and robustness of handcrafted Visual Place Recognition pipelines. This paper aims to help academic researchers and companies in the hardware and software industry co-design VPR solutions and expand the use of VPR algorithms in commercial products.
  arXiv  Detail & Related papers  (2023-05-09T21:34:38Z)
• Single Image Depth Prediction Made Better: A Multivariate Gaussian Take [163.14849753700682]
  We introduce an approach that performs continuous modeling of per-pixel depth. Our method's accuracy (named MG) is among the top on the KITTI depth-prediction benchmark leaderboard.
  arXiv  Detail & Related papers  (2023-03-31T16:01:03Z)
• Generating Superpixels for High-resolution Images with Decoupled Patch Calibration [82.21559299694555]
  Patch Networks (PCNet) is designed to efficiently and accurately implement high-resolution superpixel segmentation. DPC takes a local patch from the high-resolution images and dynamically generates a binary mask to impose the network to focus on region boundaries. In particular, DPC takes a local patch from the high-resolution images and dynamically generates a binary mask to impose the network to focus on region boundaries.
  arXiv  Detail & Related papers  (2021-08-19T10:33:05Z)
• High-Resolution Depth Maps Based on TOF-Stereo Fusion [27.10059147107254]
  We propose a novel TOF-stereo fusion method based on an efficient seed-growing algorithm. We show that the proposed algorithm outperforms 2D image-based stereo algorithms. The algorithm potentially exhibits real-time performance on a single CPU.
  arXiv  Detail & Related papers  (2021-07-30T15:11:42Z)
• Lighter Stacked Hourglass Human Pose Estimation [0.0]
  We focus on one of the deep learning-based approaches of human pose estimation proposed by Newell et al. Their approach is widely used in many applications and is regarded as one of the best works in this area. In this study, we study the effect of architectural modifications on the computational speed and accuracy of the network.
  arXiv  Detail & Related papers  (2021-07-28T21:05:34Z)
• 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos [107.36352212367179]
  We propose RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed method is able to learn 3D body pose and shape across different resolutions with one single model. We extend the RSC-Net to handle low-resolution videos and apply it to reconstruct textured 3D pedestrians from low-resolution input.
  arXiv  Detail & Related papers  (2021-03-11T06:52:12Z)
• Exploiting Raw Images for Real-Scene Super-Resolution [105.18021110372133]
  We study the problem of real-scene single image super-resolution to bridge the gap between synthetic data and real captured images. We propose a method to generate more realistic training data by mimicking the imaging process of digital cameras. We also develop a two-branch convolutional neural network to exploit the radiance information originally-recorded in raw images.
  arXiv  Detail & Related papers  (2021-02-02T16:10:15Z)
• Multi-Scale Progressive Fusion Learning for Depth Map Super-Resolution [11.072332820377612]
  The resolution of depth map collected by depth camera is often lower than that of its associated RGB camera. A major problem with depth map super-resolution is that there will be obvious jagged edges and excessive loss of details. We propose a multi-scale progressive fusion network for depth map SR, which possess an structure to integrate hierarchical features in different domains.
  arXiv  Detail & Related papers  (2020-11-24T03:03:07Z)
• 3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning [105.49950571267715]
  Existing deep learning methods for 3D human shape and pose estimation rely on relatively high-resolution input images. We propose RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. We show that both these new training losses provide robustness when learning 3D shape and pose in a weakly-supervised manner.
  arXiv  Detail & Related papers  (2020-07-27T16:19:52Z)
• PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models [77.32079593577821]
  PULSE (Photo Upsampling via Latent Space Exploration) generates high-resolution, realistic images at resolutions previously unseen in the literature. Our method outperforms state-of-the-art methods in perceptual quality at higher resolutions and scale factors than previously possible.
  arXiv  Detail & Related papers  (2020-03-08T16:44:31Z)

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.