AIConfPaper
← Search

Ayan Das

7 accepted papers

2024

Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes

Hmrishav Bandyopadhyay, Subhadeep Koley, Ayan Das, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury +2
CVPR 2024poster

In this paper we democratise 3D content creation enabling precise generation of 3D shapes from abstract sketches while overcoming limitations tied to drawing skills. We introduce a novel part-level modelling and alignment framework that facilitates abstraction modelling and cross-modal correspondenc…

Cited by 32Source ↗PDF ↗code ↗Scholar ↗
2024

Modelling complex vector drawings with stroke-clouds

Alexander Ashcroft, Ayan Das, Yulia Gryaditskaya, Zhiyu Qu, Yi-Zhe Song
ICLR 2024poster

Vector drawings are innately interactive as they preserve creational cues. Despite this desirable property they remain relatively under explored due to the difficulties in modeling complex vector drawings. This is in part due to the primarily _sequential and auto-regressive nature_ of existing appro…

Cited by 3Source ↗PDF ↗Scholar ↗
2023

ChiroDiff: Modelling chirographic data with Diffusion Models

Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song
ICLR 2023poster

Generative modelling over continuous-time geometric constructs, a.k.a $chirographic\ data$ such as handwriting, sketches, drawings etc., have been accomplished through autoregressive distributions. Such strictly-ordered discrete factorization however falls short of capturing key properties of chirog…

Cited by 16Source ↗PDF ↗Scholar ↗
2023

Image generation with shortest path diffusion

Ayan Das, Stathi Fotiadis, Anil Batra, Farhang Nabiei, FengTing Liao, Sattar Vakili +2
ICML 2023poster

The field of image generation has made significant progress thanks to the introduction of Diffusion Models, which learn to progressively reverse a given image corruption. Recently, a few studies introduced alternative ways of corrupting images in Diffusion Models, with an emphasis on blurring. Howev…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2022

SketchODE: Learning neural sketch representation in continuous time

Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song
ICLR 2022poster

Learning meaningful representations for chirographic drawing data such as sketches, handwriting, and flowcharts is a gateway for understanding and emulating human creative expression. Despite being inherently continuous-time data, existing works have treated these as discrete-time sequences, disrega…

Cited by 18Source ↗PDF ↗Scholar ↗
2021

Cloud2Curve: Generation and Vectorization of Parametric Sketches

Ayan Das, Yongxin Yang, Timothy M. Hospedales, Tao Xiang, Yi-Zhe Song
CVPR 2021poster

Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations. We further aim to model sketches as a sequence of low-dimensional parametric curves. To this end, we propose an inverse graphics framework capable of a…

Cited by 42PDF ↗Scholar ↗
2020

BézierSketch: A generative model for scalable vector sketches

Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song
ECCV 2020poster

The study of neural generative models of human sketches is a fascinating contemporary modeling problem due to the links between sketch image generation and the human drawing process. The landmark SketchRNN provided breakthrough by sequentially generating sketches as a sequence of waypoints. However…

Cited by 63Source ↗PDF ↗code ↗Scholar ↗