Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Zharkov, Ilya"'
We introduce motion graph, a novel approach to the video prediction problem, which predicts future video frames from limited past data. The motion graph transforms patches of video frames into interconnected graph nodes, to comprehensively describe t
Externí odkaz:
http://arxiv.org/abs/2410.22288
Autor:
Selvaraju, Pratheba, Abrevaya, Victoria Fernandez, Bolkart, Timo, Akkerman, Rick, Ding, Tianyu, Amjadi, Faezeh, Zharkov, Ilya
Reconstructing 3D face models from a single image is an inherently ill-posed problem, which becomes even more challenging in the presence of occlusions. In addition to fewer available observations, occlusions introduce an extra source of ambiguity, w
Externí odkaz:
http://arxiv.org/abs/2410.21629
Autor:
Chen, Tianyi, Qu, Xiaoyi, Aponte, David, Banbury, Colby, Ko, Jongwoo, Ding, Tianyu, Ma, Yong, Lyapunov, Vladimir, Zharkov, Ilya, Liang, Luming
Structured pruning is one of the most popular approaches to effectively compress the heavy deep neural networks (DNNs) into compact sub-networks while retaining performance. The existing methods suffer from multi-stage procedures along with significa
Externí odkaz:
http://arxiv.org/abs/2409.09085
Diffusion transformers (DiT) have become the de facto choice for generating high-quality images and videos, largely due to their scalability, which enables the construction of larger models for enhanced performance. However, the increased size of the
Externí odkaz:
http://arxiv.org/abs/2407.01425
Existing angle-based contour descriptors suffer from lossy representation for non-starconvex shapes. By and large, this is the result of the shape being registered with a single global inner center and a set of radii corresponding to a polar coordina
Externí odkaz:
http://arxiv.org/abs/2404.08292
Autor:
Wang, Guangzhi, Chen, Tianyi, Ghasedi, Kamran, Wu, HsiangTao, Ding, Tianyu, Nuesmeyer, Chris, Zharkov, Ilya, Kankanhalli, Mohan, Liang, Luming
Face attribute editing plays a pivotal role in various applications. However, existing methods encounter challenges in achieving high-quality results while preserving identity, editing faithfulness, and temporal consistency. These challenges are root
Externí odkaz:
http://arxiv.org/abs/2404.08111
Autor:
Chen, Tianyi, Ding, Tianyu, Zhu, Zhihui, Chen, Zeyu, Wu, HsiangTao, Zharkov, Ilya, Liang, Luming
Compressing a predefined deep neural network (DNN) into a compact sub-network with competitive performance is crucial in the efficient machine learning realm. This topic spans various techniques, from structured pruning to neural architecture search,
Externí odkaz:
http://arxiv.org/abs/2312.09411
Autor:
Ding, Tianyu, Chen, Tianyi, Zhu, Haidong, Jiang, Jiachen, Zhong, Yiqi, Zhou, Jinxin, Wang, Guangzhi, Zhu, Zhihui, Zharkov, Ilya, Liang, Luming
The rapid growth of Large Language Models (LLMs) has been a driving force in transforming various domains, reshaping the artificial general intelligence landscape. However, the increasing computational and memory demands of these models present subst
Externí odkaz:
http://arxiv.org/abs/2312.00678
Autor:
Zhou, Jinxin, Ding, Tianyu, Chen, Tianyi, Jiang, Jiachen, Zharkov, Ilya, Zhu, Zhihui, Liang, Luming
We present DREAM, a novel training framework representing Diffusion Rectification and Estimation Adaptive Models, requiring minimal code changes (just three lines) yet significantly enhancing the alignment of training with sampling in diffusion model
Externí odkaz:
http://arxiv.org/abs/2312.00210
Generalizability and few-shot learning are key challenges in Neural Radiance Fields (NeRF), often due to the lack of a holistic understanding in pixel-level rendering. We introduce CaesarNeRF, an end-to-end approach that leverages scene-level CAlibra
Externí odkaz:
http://arxiv.org/abs/2311.15510