Text-to-3D models lose prompt sensitivity for out-of-distribution shapes due to sink traps but retain geometric diversity via unconditional priors, enabling a decoupled inversion method for robust editing.
Advances in Neural Information Processing Systems37, 34513–34532 (2024)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Derives LMMSE-based optimal estimators for blind inverse problems that are equivalent to tailored Tikhonov regularization and provides finite-sample error bounds explicitly depending on operator randomness.
citing papers explorer
-
Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes
Text-to-3D models lose prompt sensitivity for out-of-distribution shapes due to sink traps but retain geometric diversity via unconditional priors, enabling a decoupled inversion method for robust editing.
-
On the Sample Complexity of Learning for Blind Inverse Problems
Derives LMMSE-based optimal estimators for blind inverse problems that are equivalent to tailored Tikhonov regularization and provides finite-sample error bounds explicitly depending on operator randomness.