no code implementations • 30 Mar 2024 • Vaibhav Vavilala, Rahul Vasanth, David Forsyth
Learned methods for restoring low fidelity renders are highly developed, because suppressing render noise means one can save compute and use fast renders with few rays per pixel.
no code implementations • ICCV 2023 • Vaibhav Vavilala, David Forsyth
Our method uses a learned regression procedure to parse a scene into a fixed number of convexes from RGBD input, and can optionally accept segmentations to improve the decomposition.
no code implementations • 7 Jul 2023 • Vaibhav Vavilala, Seemandhar Jain, Rahul Vasanth, Anand Bhattad, David Forsyth
We present Blocks2World, a novel method for 3D scene rendering and editing that leverages a two-step process: convex decomposition of images and conditioned synthesis.
no code implementations • 6 Jul 2023 • Vaibhav Vavilala, David Forsyth
We demonstrate two novel editing procedures in the context of fantasy card art.
no code implementations • 19 Aug 2021 • Vaibhav Vavilala, David Forsyth
While noise inputs to StyleGAN2 are essential for good synthesis, we find that coarse-scale noise interferes with latent variables on this dataset because both control long-scale image effects.