Kernel interpolation with a constant multiplier scales convolution and fully-connected layers in neural networks to higher resolutions or dimensions without training, producing competitive results on Stable Diffusion and other models.
Bridging the gap: Consistent image outpainting via training- free noise optimization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Supersampling Stable Diffusion and Beyond: A Seamless, Training-Free Approach for Scaling Neural Networks Using Common Interpolation Methods
Kernel interpolation with a constant multiplier scales convolution and fully-connected layers in neural networks to higher resolutions or dimensions without training, producing competitive results on Stable Diffusion and other models.
- HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos