Using VLM-generated body-part text as a learned pose constraint in diffusion-based optimization gives small PA-MPJPE gains on 3DPW and Human3.6M, with mixed MPJPE results.
End-to-end recovery of human shape and pose,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Adapting Human Mesh Recovery with Vision-Language Feedback
Using VLM-generated body-part text as a learned pose constraint in diffusion-based optimization gives small PA-MPJPE gains on 3DPW and Human3.6M, with mixed MPJPE results.