Super Resolution in Human Pose Estimation: Pixelated Poses to a Resolution Result?

• URL: http://arxiv.org/abs/2107.02108v1
• Date: Mon, 5 Jul 2021 16:06:55 GMT
• Title: Super Resolution in Human Pose Estimation: Pixelated Poses to a Resolution Result?
• Authors: Peter Hardy, Srinandan Dasmahapatra, Hansung Kim
• Abstract summary: We introduce a novel Mask-RCNN approach to decide when to use SR during the keypoint detection step. We find that for low resolution people their keypoint detection performance improved once SR was applied. To address this we introduced a novel Mask-RCNN approach, utilising a segmentation area threshold to decide when to use SR during the keypoint detection step.
• Score: 9.577509224534323
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The results obtained from state of the art human pose estimation (HPE) models degrade rapidly when evaluating people of a low resolution, but can super resolution (SR) be used to help mitigate this effect? By using various SR approaches we enhanced two low resolution datasets and evaluated the change in performance of both an object and keypoint detector as well as end-to-end HPE results. We remark the following observations. First we find that for low resolution people their keypoint detection performance improved once SR was applied. Second, the keypoint detection performance gained is dependent on the persons initial resolution (segmentation area in pixels) in the original image; keypoint detection performance was improved when SR was applied to people with a small initial segmentation area, but degrades as this becomes larger. To address this we introduced a novel Mask-RCNN approach, utilising a segmentation area threshold to decide when to use SR during the keypoint detection step. This approach achieved the best results for each of our HPE performance metrics.

Related papers

• SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation [39.936860590417346]
  We propose a framework that only uses Sparse High-resolution Representations for human Pose estimation (SHaRPose) Our model SHaRPose-Base achieves 77.4 AP (+0.5 AP) on the validation set and 76.7 AP (+0.5 AP) on the COCO test-dev set, and infers at a speed of $1.4times$ faster than ViTPose-Base.
  arXiv  Detail & Related papers  (2023-12-17T16:29:16Z)
• Improving Performance of Object Detection using the Mechanisms of Visual Recognition in Humans [0.4297070083645048]
  We first track the performance of the state-of-the-art deep object recognition network, Faster- RCNN, as a function of image resolution. They also show that different spatial frequencies convey different information about the objects in recognition process. We propose a multi-resolution object recognition framework rather than a single-resolution network.
  arXiv  Detail & Related papers  (2023-01-23T19:09:36Z)
• MrSARP: A Hierarchical Deep Generative Prior for SAR Image Super-resolution [0.5161531917413706]
  We present a novel hierarchical deep-generative model MrSARP for SAR imagery. MrSARP is trained in conjunction with a critic that scores multi resolution images jointly to decide if they are realistic images of a target at different resolutions. We show how this deep generative model can be used to retrieve the high spatial resolution image from low resolution images of the same target.
  arXiv  Detail & Related papers  (2022-11-30T19:12:21Z)
• Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection [77.3530907443279]
  We propose a novel self-supervised framework to detect objects in degraded low resolution images. Our methods has achieved superior performance compared with existing methods when facing variant degradation situations.
  arXiv  Detail & Related papers  (2022-08-05T09:36:13Z)
• Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution [64.15915577164894]
  A hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing. HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.
  arXiv  Detail & Related papers  (2022-06-07T14:55:32Z)
• SALISA: Saliency-based Input Sampling for Efficient Video Object Detection [58.22508131162269]
  We propose SALISA, a novel non-uniform SALiency-based Input SAmpling technique for video object detection. We show that SALISA significantly improves the detection of small objects.
  arXiv  Detail & Related papers  (2022-04-05T17:59:51Z)
• FasterPose: A Faster Simple Baseline for Human Pose Estimation [65.8413964785972]
  We propose a design paradigm for cost-effective network with LR representation for efficient pose estimation, named FasterPose. We study the training behavior of FasterPose, and formulate a novel regressive cross-entropy (RCE) loss function for accelerating the convergence. Compared with the previously dominant network of pose estimation, our method reduces 58% of the FLOPs and simultaneously gains 1.3% improvement of accuracy.
  arXiv  Detail & Related papers  (2021-07-07T13:39:08Z)
• Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution [10.960291115491504]
  We generate an artifact-free high-resolution image from a low-resolution one compressed with an arbitrary quality factor. A context-aware joint CAR and SR neural network (CAJNN) integrates both local and non-local features to solve CAR and SR in one-stage. A deep reconstruction network is adopted to predict high quality and high-resolution images.
  arXiv  Detail & Related papers  (2020-10-18T04:17:08Z)
• Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates [76.51095823248104]
  We present several schemes that are rarely or unthoroughly studied before for improving keypoint detection and grouping (keypoint regression) performance. First, we exploit the keypoint heatmaps for pixel-wise keypoint regression instead of separating them for improving keypoint regression. Second, we adopt a pixel-wise spatial transformer network to learn adaptive representations for handling the scale and orientation variance. Third, we present a joint shape and heatvalue scoring scheme to promote the estimated poses that are more likely to be true poses.
  arXiv  Detail & Related papers  (2020-06-28T01:14:59Z)
• Feature-Driven Super-Resolution for Object Detection [13.748941620767452]
  This paper proposes a simple but powerful feature-driven super-resolution (FDSR) to improve the detection performance of low-resolution (LR) images. FDSR outperforms the detection performance mAP on MS COCO validation, VOC2007 databases with good generalization to other detection networks.
  arXiv  Detail & Related papers  (2020-04-01T16:33:07Z)
• 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.