6 papers
Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising
Yifan Wang, Liya Ji, Zhanghan Ke +3
We propose an approach to enhancing synthetic video realism, which can re-render synthetic videos from a simulator in photorealistic fashion. Our realism enhancement approach is a…
ART-DECO: Arbitrary Text Guidance for 3D Detailizer Construction
Qimin Chen, Yuezhi Yang, Wang Yifan +4
We introduce a 3D detailizer, a neural model which can instantaneously (in <1s) transform a coarse 3D shape proxy into a high-quality asset with detailed geometry and texture as gu…
3D Engine-ready Photorealistic Avatars via Dynamic Textures
Yifan Wang, Ivan Molodetskikh, Ondrej Texler +1
As the digital and physical worlds become more intertwined, there has been a lot of interest in digital avatars that closely resemble their real-world counterparts. Current digitiz…
Inverse Painting: Reconstructing The Painting Process
Bowei Chen, Yifan Wang, Brian Curless +2
Given an input painting, we reconstruct a time-lapse video of how it may have been painted. We formulate this as an autoregressive image generation problem, in which an initially b…
Ambisonizer: Neural Upmixing as Spherical Harmonics Generation
Yongyi Zang, Yifan Wang, Minglun Lee
Neural upmixing, the task of generating immersive music with an increased number of channels from fewer input channels, has been an active research area, with mono-to-stereo and st…
Infinite Texture: Text-guided High Resolution Diffusion Texture Synthesis
Yifan Wang, Aleksander Holynski, Brian L. Curless +1
We present Infinite Texture, a method for generating arbitrarily large texture images from a text prompt. Our approach fine-tunes a diffusion model on a single texture, and learns…