VS3D performs local 3D asset editing by injecting reconstruction-anchored source signals, partial-mean guidance, and twin-agreement residuals into the velocity sampler to control edit strength and preserve identity.
Efros, Aleksander Holynski, and Angjoo Kanazawa
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Pxform dataset and PartFlow network enable feedforward 3D editing by learning from semantic-part transformations and achieve SOTA on geometric and appearance benchmarks.
citing papers explorer
-
Velocity-Space 3D Asset Editing
VS3D performs local 3D asset editing by injecting reconstruction-anchored source signals, partial-mean guidance, and twin-agreement residuals into the velocity sampler to control edit strength and preserve identity.
-
Feedforward 3D Editing Learns from Semantic-Part Transformation
Pxform dataset and PartFlow network enable feedforward 3D editing by learning from semantic-part transformations and achieve SOTA on geometric and appearance benchmarks.