Zobrazeno 1 - 10
of 124
pro vyhledávání: '"Bhunia, Ayan Kumar"'
Autor:
Bandyopadhyay, Hmrishav, Chowdhury, Pinaki Nath, Sain, Aneeshan, Koley, Subhadeep, Xiang, Tao, Bhunia, Ayan Kumar, Song, Yi-Zhe
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 representation learning (e.g., classification). This generalisation ha
Externí odkaz:
http://arxiv.org/abs/2407.03893
In this paper, we delve into the intricate dynamics of Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) by addressing a critical yet overlooked aspect -- the choice of viewpoint during sketch creation. Unlike photo systems that seamlessly handle d
Externí odkaz:
http://arxiv.org/abs/2407.01810
Autor:
Utintu, Chaitat, Chowdhury, Pinaki Nath, Sain, Aneeshan, Koley, Subhadeep, Bhunia, Ayan Kumar, Song, Yi-Zhe
This paper introduces a novel approach to sketch colourisation, inspired by the universal childhood activity of colouring and its professional applications in design and story-boarding. Striking a balance between precision and convenience, our method
Externí odkaz:
http://arxiv.org/abs/2405.18716
Autor:
Bandyopadhyay, Hmrishav, Bhunia, Ayan Kumar, Chowdhury, Pinaki Nath, Sain, Aneeshan, Xiang, Tao, Hospedales, Timothy, Song, Yi-Zhe
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 dimension that implicitly encodes the underlying shape as a function of tim
Externí odkaz:
http://arxiv.org/abs/2403.09344
Autor:
Bandyopadhyay, Hmrishav, Chowdhury, Pinaki Nath, Bhunia, Ayan Kumar, Sain, Aneeshan, Xiang, Tao, Song, Yi-Zhe
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 explanations of network behavior, we discern the genuine implications
Externí odkaz:
http://arxiv.org/abs/2403.09480
Autor:
Koley, Subhadeep, Bhunia, Ayan Kumar, Sekhri, Deeptanshu, Sain, Aneeshan, Chowdhury, Pinaki Nath, Xiang, Tao, Song, Yi-Zhe
This paper unravels the potential of sketches for diffusion models, addressing the deceptive promise of direct sketch control in generative AI. We importantly democratise the process, enabling amateur sketches to generate precise images, living up to
Externí odkaz:
http://arxiv.org/abs/2403.07234
Autor:
Koley, Subhadeep, Bhunia, Ayan Kumar, Sain, Aneeshan, Chowdhury, Pinaki Nath, Xiang, Tao, Song, Yi-Zhe
Two primary input modalities prevail in image retrieval: sketch and text. While text is widely used for inter-category retrieval tasks, sketches have been established as the sole preferred modality for fine-grained image retrieval due to their abilit
Externí odkaz:
http://arxiv.org/abs/2403.07222
Autor:
Koley, Subhadeep, Bhunia, Ayan Kumar, Sain, Aneeshan, Chowdhury, Pinaki Nath, Xiang, Tao, Song, Yi-Zhe
In this paper, we propose a novel abstraction-aware sketch-based image retrieval framework capable of handling sketch abstraction at varied levels. Prior works had mainly focused on tackling sub-factors such as drawing style and order, we instead att
Externí odkaz:
http://arxiv.org/abs/2403.07203
Autor:
Koley, Subhadeep, Bhunia, Ayan Kumar, Sain, Aneeshan, Chowdhury, Pinaki Nath, Xiang, Tao, Song, Yi-Zhe
This paper, for the first time, explores text-to-image diffusion models for Zero-Shot Sketch-based Image Retrieval (ZS-SBIR). We highlight a pivotal discovery: the capacity of text-to-image diffusion models to seamlessly bridge the gap between sketch
Externí odkaz:
http://arxiv.org/abs/2403.07214
Autor:
Bandyopadhyay, Hmrishav, Koley, Subhadeep, Das, Ayan, Bhunia, Ayan Kumar, Sain, Aneeshan, Chowdhury, Pinaki Nath, Xiang, Tao, Song, Yi-Zhe
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
Externí odkaz:
http://arxiv.org/abs/2312.04043