3 papers
cs.GR2026
Monte Carlo Rendering to Diffusion Curves with Differential BEM
Ryusuke Sugimoto, Christopher Batty, Siddhartha Chaudhuri +4
We present a method for generating vector graphics, in the form of diffusion curves, directly from noisy samples produced by a Monte Carlo renderer. While generating raster images…
cs.LG2025
Mean-Shift Distillation for Diffusion Mode Seeking
Vikas Thamizharasan, Nikitas Chatzis, Iliyan Georgiev +5
We present mean-shift distillation, a novel diffusion distillation technique that provides a provably good proxy for the gradient of the diffusion output distribution. This is deri…
cs.CV2024
NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation
Vikas Thamizharasan, Difan Liu, Matthew Fisher +3
The success of denoising diffusion models in representing rich data distributions over 2D raster images has prompted research on extending them to other data representations, such…