DiffPose: Reliable 2D Pose Estimation Through Denoising Diffusion
- Resource Type
- Conference
- Authors
- Jinwei, Liu; Feng, Zhang; Lei, Chen
- Source
- 2023 China Automation Congress (CAC) Automation Congress (CAC), 2023 China. :4041-4046 Nov, 2023
- Subject
- Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Heating systems
Uncertainty
Pose estimation
Noise reduction
Diffusion processes
Predictive models
Benchmark testing
2D Human Pose Estimation
Diffusion Model
Joint Position Disturbance
- Language
- ISSN
- 2688-0938
We present DiffPose, a novel framework for 2D human pose estimation. DiffPose is capable of generating reliable lower-uncertainty heatmap from noise using a given image. DiffPose differs from previous methods in that it corrects the deviation in its own predictions without designing additional pose refinement modules. To accomplish these, we introduce a forward diffusion process that converts the heatmap into random noise. We then employ iterative denoising to generate reliable pose estimation during the reverse diffusion process. Extensive experiments on the well-recognized MS-COCO benchmark demonstrate the superior reliability of DiffPose compared to previously well-established detectors.