Personal website of Ayan Das
Paper Abstract The sampling process of Denoising Diffusion Probabilistic Models (DDPMs) can be accelerated by leveraging second-order information in the form of approximations to the denoising posterior covariance – allowing samples of acceptable quality to be produced in fewer but larger sampling steps. Previous attempts at using such information have used drastic (e.g. diagonal) simplifications…
Paper Abstract Score estimation has led to several state-of-the-art generative models, particularly in computer vision. Compared to maximum likelihood, one of the key advantages of score estimation is that it does not require the calculation of a normalization factor. However, explicit score matching necessitates knowledge of the true score of the data distribution, which is typically unavailable.…
Paper Code Abstract The problem of sketch semantic segmentation is far from being solved. Despite existing methods exhibiting near-saturating performances on simple sketches with high recognisability, they suffer serious setbacks when the target sketches are products of an imaginative process with high degree of creativity. We hypothesise that human creativity, being highly individualistic,…
Paper Code Abstract 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 approaches failing to scale beyond simple drawings. In this paper, we define generative…
Paper (self-hosted) Paper (arXiv) Webpage Abstract 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 correspondence. Leveraging the same part-level decoder, our…
Abstract Diffusion Model, a new generative model family, has taken the world by storm after the seminal paper by Ho et al. (2020) . While diffusion models are often described as a probabilistic Markov Chain, their fundamental principle lies in the decade-old theory of Stochastic Differential Equation (SDE), as found out later by Song et al. (2021) . In this article, we will go back and revisit the…
Paper (axXiv) Code Asbtract Recently, Zhang and Chen (2023) have proposed the Diffusion Exponential Integrator Sampler (DEIS) for fast generation of samples from Diffusion Models. It leverages the semi-linear nature of the probability flow ordinary differential equation (ODE) in order to greatly reduce integration error and improve generation quality at low numbers of function evaluations (NFEs).…
Paper (official) Paper (axXiv) Code Asbtract 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. However, these studies are purely empirical and it remains…
Paper (official) Paper (arXiv) Code Abstract 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 chirographic data – it fails to build holistic understanding of…
Paper Code Abstract 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, disregarding their true nature. In this work, we model such data as continuous-time…
Paper (official) Paper (arXiv) Abstract 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 approximating a raster or waypoint based stroke encoded as a…
Paper Supplementary Code Abstract We present the first competitive drawing agent Pixelor that exhibits human-level performance at a Pictionary-like sketching game, where the participant whose sketch is recognized first is a winner. Our AI agent can autonomously sketch a given visual concept, and achieve a recognizable rendition as quickly or faster than a human competitor. The key to victory for…
Paper Supplementary Code Abstract 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 this leads to low-resolution image generation, and failure to…
Paper Abstract Feature Selection (FS) is an important pre-processing step in machine learning and it reduces the number of features/variables used to describe each member of a dataset. Such reduction occurs by eliminating some of the non-discriminating and redundant features and selecting a subset of the existing features with higher discriminating power among various classes in the data. In this…
Paper Abstract This paper presents a novel approach towards Indic handwritten word recognition using zone-wise information. Because of complex nature due to compound characters, modifiers, overlapping and touching, etc., character segmentation and recognition is a tedious job in Indic scripts (e.g. Devanagari, Bangla, Gurumukhi, and other similar scripts). To avoid character segmentation in such…