11 citations · 16 across the 14 of their papers we have counts for
15 papers
Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation
Hmrishav Bandyopadhyay, Xuanchi Ren, Zijian Huang +7
Interactive autoregressive video generation demands both low-latency rollouts and precise online control. Few-step distillation accelerates generation by reducing denoising steps,…
Block Cascading: Training Free Acceleration of Block-Causal Video Models
Hmrishav Bandyopadhyay, Nikhil Pinnaparaju, Rahim Entezari +3
Block-causal video generation faces a stark speed-quality trade-off: small 1.3B models manage only 16 FPS while large 14B models crawl at 4.5 FPS, forcing users to choose between r…
SD3.5-Flash: Distribution-Guided Distillation of Generative Flows
Hmrishav Bandyopadhyay, Rahim Entezari, Jim Scott +3
We present SD3.5-Flash, an efficient few-step distillation framework that brings high-quality image generation to accessible consumer devices. Our approach distills computationally…
Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models
Dar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou +1
Negative guidance -- explicitly suppressing unwanted attributes -- remains a fundamental challenge in diffusion models, particularly in few-step sampling regimes. While Classifier-…
NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training
Dar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou +1
We introduce NitroFusion, a fundamentally different approach to single-step diffusion that achieves high-quality generation through a dynamic adversarial framework. While one-step…
FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations
Hmrishav Bandyopadhyay, Yi-Zhe Song
Sketch animations offer a powerful medium for visual storytelling, from simple flip-book doodles to professional studio productions. While traditional animation requires teams of s…
Incremental Open-set Domain Adaptation
Sayan Rakshit, Hmrishav Bandyopadhyay, Nibaran Das +1
Catastrophic forgetting makes neural network models unstable when learning visual domains consecutively. The neural network model drifts to catastrophic forgetting-induced low perf…
Do Generalised Classifiers really work on Human Drawn Sketches?
Hmrishav Bandyopadhyay, Pinaki Nath Chowdhury, Aneeshan Sain +4
This paper, for the first time, marries large foundation models with human sketch understanding. We demonstrate what this brings -- a paradigm shift in terms of generalised sketch…
What Sketch Explainability Really Means for Downstream Tasks
Hmrishav Bandyopadhyay, Pinaki Nath Chowdhury, Ayan Kumar Bhunia +3
In this paper, we explore the unique modality of sketch for explainability, emphasising the profound impact of human strokes compared to conventional pixel-oriented studies. Beyond…
SketchINR: A First Look into Sketches as Implicit Neural Representations
Hmrishav Bandyopadhyay, Ayan Kumar Bhunia, Pinaki Nath Chowdhury +4
We propose SketchINR, to advance the representation of vector sketches with implicit neural models. A variable length vector sketch is compressed into a latent space of fixed dimen…
Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes
Hmrishav Bandyopadhyay, Subhadeep Koley, Ayan Das +5
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…
Cryo-shift: Reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization
Hmrishav Bandyopadhyay, Zihao Deng, Leiting Ding +5
Cryo-Electron Tomography (cryo-ET) is a 3D imaging technology that enables the visualization of subcellular structures in situ at near-atomic resolution. Cellular cryo-ET images he…
A distillation based approach for the diagnosis of diseases
Hmrishav Bandyopadhyay, Shuvayan Ghosh Dastidar, Bisakh Mondal +2
Presently, Covid-19 is a serious threat to the world at large. Efforts are being made to reduce disease screening times and in the development of a vaccine to resist this disease,…
RectiNet-v2: A stacked network architecture for document image dewarping
Hmrishav Bandyopadhyay, Tanmoy Dasgupta, Nibaran Das +1
With the advent of mobile and hand-held cameras, document images have found their way into almost every domain. Dewarping of these images for the removal of perspective distortions…
A Gated and Bifurcated Stacked U-Net Module for Document Image Dewarping
Hmrishav Bandyopadhyay, Tanmoy Dasgupta, Nibaran Das +1
Capturing images of documents is one of the easiest and most used methods of recording them. These images however, being captured with the help of handheld devices, often lead to u…