Human 3D keypoints via spatial uncertainty modeling
We introduce a technique for 3D human keypoint estimation that directly models the notion of spatial uncertainty of a keypoint. Our technique employs a principled approach to modelling spatial uncertainty inspired from techniques in robust statistics. Furthermore, our pipeline requires no 3D ground truth labels, relying instead on (possibly noisy) 2D image-level keypoints. Our method achieves near state-of-the-art performance on Human3.6m while being efficient to evaluate and straightforward to
Code (0)
등록된 구현이 없습니다.
Tasks
Keypoint EstimationSimilar Papers 제목 키워드 기반
KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints
Image-based volumetric humans using pixel-aligned features promise generalization to unseen poses and identities. Prior work leverages global spatial encodings and multi-view geometric consistency to reduce spatial ambig…
3D Face Reconstruction3D Human ReconstructionGeneralizable Novel View SynthesisNovel View SynthesisFew-shot Keypoint Detection with Uncertainty Learning for Unseen Species
Current non-rigid object keypoint detectors perform well on a chosen kind of species and body parts, and require a large amount of labelled keypoints for training. Moreover, their heatmaps, tailored to specific body part…
Fine-Grained Visual RecognitionKeypoint DetectionRepresentation LearningMV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation
While significant progress has been made in single-view 3D human pose estimation, multi-view 3D human pose estimation remains challenging, particularly in terms of generalizing to new camera configurations. Existing …
3D Human Pose EstimationMulti-view 3D Human Pose EstimationPose EstimationRethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation
In keypoint estimation tasks such as human pose estimation, heatmap-based regression is the dominant approach despite possessing notable drawbacks: heatmaps intrinsically suffer from quantization error and require excess…
Keypoint EstimationPose EstimationMV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation
While significant progress has been made in single-view 3D human pose estimation, multi-view 3D human pose estimation remains challenging, particularly in terms of generalizing to new camera configurations. Existing atte…
3D Human Pose Estimation