OCHuman
PulseAugur coverage of OCHuman — every cluster mentioning OCHuman across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New protocol reveals OKS-mAP blind spots in 2D pose estimation
A new evaluation protocol has been developed to address the limitations of the OKS-mAP metric in 2D human pose estimation. This protocol introduces three modules to assess occlusion, joint-angle error, and temporal stab…
-
DETRPose: Real-time transformer models for multi-person pose estimation unveiled
Researchers have introduced DETRPose, a novel family of transformer-based models designed for real-time, end-to-end multi-person pose estimation. This approach significantly enhances the GroupPose decoder to achieve rea…
-
TrioPose framework enhances multi-person image generation with diffusion transformers
Researchers have developed TrioPose, a novel framework for pose-guided text-to-image generation that addresses challenges in complex multi-person scenarios. Built on the SD3.5M architecture, TrioPose utilizes a Triple-S…