On Coordinate Decoding for Keypoint Estimation Tasks
- URL: http://arxiv.org/abs/2110.10289v1
- Date: Tue, 19 Oct 2021 22:14:48 GMT
- Title: On Coordinate Decoding for Keypoint Estimation Tasks
- Authors: Anargyros Chatzitofis, Nikolaos Zioulis, Georgios Nikolaos Albanis,
Dimitrios Zarpalas, Petros Daras
- Abstract summary: A series of 2D (and 3D) keypoint estimation tasks are built upon heatmap coordinate representation.
Heatmap coordinate representation allows for learnable and spatially aware encoding and decoding of keypoint coordinates on grids.
- Score: 22.603579615063495
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A series of 2D (and 3D) keypoint estimation tasks are built upon heatmap
coordinate representation, i.e. a probability map that allows for learnable and
spatially aware encoding and decoding of keypoint coordinates on grids, even
allowing for sub-pixel coordinate accuracy. In this report, we aim to reproduce
the findings of DARK that investigated the 2D heatmap representation by
highlighting the importance of the encoding of the ground truth heatmap and the
decoding of the predicted heatmap to keypoint coordinates. The authors claim
that a) a more principled distribution-aware coordinate decoding method
overcomes the limitations of the standard techniques widely used in the
literature, and b), that the reconstruction of heatmaps from ground-truth
coordinates by generating accurate and continuous heatmap distributions lead to
unbiased model training, contrary to the standard coordinate encoding process
that quantizes the keypoint coordinates on the resolution of the input image
grid.
Related papers
- Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features [20.935803672362283]
We introduce an innovative unsupervised keypoint detector Key-Grid for both the rigid-body and deformable objects.
We leverage the identified keypoint in formation to form a 3D grid feature heatmap called grid heatmap, which is used in the decoder section.
Key-Grid achieves the state-of-the-art performance on the semantic consistency and position accuracy of keypoints.
arXiv Detail & Related papers (2024-10-03T06:16:50Z) - CheckerPose: Progressive Dense Keypoint Localization for Object Pose
Estimation with Graph Neural Network [66.24726878647543]
Estimating the 6-DoF pose of a rigid object from a single RGB image is a crucial yet challenging task.
Recent studies have shown the great potential of dense correspondence-based solutions.
We propose a novel pose estimation algorithm named CheckerPose, which improves on three main aspects.
arXiv Detail & Related papers (2023-03-29T17:30:53Z) - SketchSampler: Sketch-based 3D Reconstruction via View-dependent Depth
Sampling [75.957103837167]
Reconstructing a 3D shape based on a single sketch image is challenging due to the large domain gap between a sparse, irregular sketch and a regular, dense 3D shape.
Existing works try to employ the global feature extracted from sketch to directly predict the 3D coordinates, but they usually suffer from losing fine details that are not faithful to the input sketch.
arXiv Detail & Related papers (2022-08-14T16:37:51Z) - Is 2D Heatmap Representation Even Necessary for Human Pose Estimation? [44.313782042852246]
We propose a textbfSimple yet promising textbfDisentangled textbfRepresentation for keypoint coordinate (emphSimDR)
In detail, we propose to disentangle the representation of horizontal and vertical coordinates for keypoint location, leading to a more efficient scheme without extra upsampling and refinement.
arXiv Detail & Related papers (2021-07-07T16:20:12Z) - P2-Net: Joint Description and Detection of Local Features for Pixel and
Point Matching [78.18641868402901]
This work takes the initiative to establish fine-grained correspondences between 2D images and 3D point clouds.
An ultra-wide reception mechanism in combination with a novel loss function are designed to mitigate the intrinsic information variations between pixel and point local regions.
arXiv Detail & Related papers (2021-03-01T14:59:40Z) - Heatmap Regression via Randomized Rounding [105.75014893647538]
We propose a simple yet effective quantization system to address the sub-pixel localization problem.
The proposed system encodes the fractional part of numerical coordinates into the ground truth heatmap using a probabilistic approach during training.
arXiv Detail & Related papers (2020-09-01T04:54:22Z) - Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement [54.29252286561449]
We propose a two-stage graph-based and model-agnostic framework, called Graph-PCNN.
In the first stage, heatmap regression network is applied to obtain a rough localization result, and a set of proposal keypoints, called guided points, are sampled.
In the second stage, for each guided point, different visual feature is extracted by the localization.
The relationship between guided points is explored by the graph pose refinement module to get more accurate localization results.
arXiv Detail & Related papers (2020-07-21T04:59:15Z) - Attentive One-Dimensional Heatmap Regression for Facial Landmark
Detection and Tracking [73.35078496883125]
We propose a novel attentive one-dimensional heatmap regression method for facial landmark localization.
First, we predict two groups of 1D heatmaps to represent the marginal distributions of the x and y coordinates.
Second, a co-attention mechanism is adopted to model the inherent spatial patterns existing in x and y coordinates.
Third, based on the 1D heatmap structures, we propose a facial landmark detector capturing spatial patterns for landmark detection on an image.
arXiv Detail & Related papers (2020-04-05T06:51:22Z) - Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection
Challenge Track Technical Report: Distribution-Aware Coordinate
Representation for Human Pose Estimation [36.73217430761146]
We focus on the coordinate representation in human pose estimation.
We propose a principled distribution-aware decoding method.
Taking them together, we formulate a novel Distribution-Aware coordinate Representation for Keypoint (DARK) method.
arXiv Detail & Related papers (2020-03-13T10:22:36Z)
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.