SnapPose3D uses diffusion models to generate and aggregate multiple 3D pose hypotheses from single 2D frames, achieving state-of-the-art results on human pose estimation benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SnapPose3D: Diffusion-Based Single-Frame 2D-to-3D Lifting of Human Poses
SnapPose3D uses diffusion models to generate and aggregate multiple 3D pose hypotheses from single 2D frames, achieving state-of-the-art results on human pose estimation benchmarks.