activity
20142023
most citedMatFormer: A Generative Model for Procedural Materials

44 citations · 87 across the 13 of their papers we have counts for

collaborators

13 papers

cs.CV2023

HoloFusion: Towards Photo-realistic 3D Generative Modeling

Animesh Karnewar, Niloy J. Mitra, Andrea Vedaldi +1

Diffusion-based image generators can now produce high-quality and diverse samples, but their success has yet to fully translate to 3D generation: existing diffusion methods can eit…

cs.GR20234 cited

ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitives

R. Kenny Jones, Paul Guerrero, Niloy J. Mitra +1

Programs are an increasingly popular representation for visual data, exposing compact, interpretable structure that supports manipulation. Visual programs are usually written in do…

cs.GR2023

Neurosymbolic Models for Computer Graphics

Daniel Ritchie, Paul Guerrero, R. Kenny Jones +4

Procedural models (i.e. symbolic programs that output visual data) are a historically-popular method for representing graphics content: vegetation, buildings, textures, etc. They o…

cs.CV20232 cited

Pix2Video: Video Editing using Image Diffusion

Duygu Ceylan, Chun-Hao Paul Huang, Niloy J. Mitra

Image diffusion models, trained on massive image collections, have emerged as the most versatile image generator model in terms of quality and diversity. They support inverting rea…

cs.CV2023

Blowing in the Wind: CycleNet for Human Cinemagraphs from Still Images

Hugo Bertiche, Niloy J. Mitra, Kuldeep Kulkarni +5

Cinemagraphs are short looping videos created by adding subtle motions to a static image. This kind of media is popular and engaging. However, automatic generation of cinemagraphs…

cs.CV20234 cited

HoloDiffusion: Training a 3D Diffusion Model using 2D Images

Animesh Karnewar, Andrea Vedaldi, David Novotny +1

Diffusion models have emerged as the best approach for generative modeling of 2D images. Part of their success is due to the possibility of training them on millions if not billion…