Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
arXiv preprint arXiv:2302.03027 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
ControlNet adds spatial conditioning controls to pretrained text-to-image diffusion models via zero convolutions for stable fine-tuning on small or large datasets.
citing papers explorer
-
Functionalization via Structure Completion and Motion Rectification
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
-
Adding Conditional Control to Text-to-Image Diffusion Models
ControlNet adds spatial conditioning controls to pretrained text-to-image diffusion models via zero convolutions for stable fine-tuning on small or large datasets.