no code implementations • 26 Jan 2023 • Aliaksandr Siarohin, Willi Menapace, Ivan Skorokhodov, Kyle Olszewski, Jian Ren, Hsin-Ying Lee, Menglei Chai, Sergey Tulyakov
We propose a novel approach for unsupervised 3D animation of non-rigid deformable objects.
no code implementations • 23 Jan 2023 • Chieh Hubert Lin, Hsin-Ying Lee, Willi Menapace, Menglei Chai, Aliaksandr Siarohin, Ming-Hsuan Yang, Sergey Tulyakov
Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which constructs and renders an unconstrainedly large and 3D-grounded environment from random noises.
no code implementations • 6 Jan 2023 • Rameen Abdal, Hsin-Ying Lee, Peihao Zhu, Menglei Chai, Aliaksandr Siarohin, Peter Wonka, Sergey Tulyakov
Finally, we propose a novel inversion method for 3D-GANs linking the latent spaces of the source and the target domains.
no code implementations • 22 Dec 2022 • Yinghao Xu, Menglei Chai, Zifan Shi, Sida Peng, Ivan Skorokhodov, Aliaksandr Siarohin, Ceyuan Yang, Yujun Shen, Hsin-Ying Lee, Bolei Zhou, Sergey Tulyakov
Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects.
no code implementations • 15 Dec 2022 • Junli Cao, Huan Wang, Pavlo Chemerys, Vladislav Shakhrai, Ju Hu, Yun Fu, Denys Makoviichuk, Sergey Tulyakov, Jian Ren
Nevertheless, to reach a similar rendering quality as NeRF, the network in NeLF is designed with intensive computation, which is not mobile-friendly.
2 code implementations • 15 Dec 2022 • Yanyu Li, Ju Hu, Yang Wen, Georgios Evangelidis, Kamyar Salahi, Yanzhi Wang, Sergey Tulyakov, Jian Ren
With the success of Vision Transformers (ViTs) in computer vision tasks, recent arts try to optimize the performance and complexity of ViTs to enable efficient deployment on mobile devices.
no code implementations • 9 Dec 2022 • IAn Huang, Panos Achlioptas, Tianyi Zhang, Sergey Tulyakov, Minhyuk Sung, Leonidas Guibas
Additionally, to measure edit locality, we define a new metric that we call part-wise edit precision.
1 code implementation • 8 Dec 2022 • Yen-Chi Cheng, Hsin-Ying Lee, Sergey Tulyakov, Alexander Schwing, LiangYan Gui
To enable interactive generation, our method supports a variety of input modalities that can be easily provided by a human, including images, text, partially observed shapes and combinations of these, further allowing to adjust the strength of each input.
no code implementations • 23 Nov 2022 • Tanzila Rahman, Hsin-Ying Lee, Jian Ren, Sergey Tulyakov, Shweta Mahajan, Leonid Sigal
Our experiments for story generation on the MUGEN, the PororoSV and the FlintstonesSV dataset show that our method not only outperforms prior state-of-the-art in generating frames with high visual quality, which are consistent with the story, but also models appropriate correspondences between the characters and the background.
no code implementations • 4 Oct 2022 • Panos Achlioptas, Maks Ovsjanikov, Leonidas Guibas, Sergey Tulyakov
To embark on this journey, we introduce and share with the research community a large-scale dataset that contains emotional reactions and free-form textual explanations for 85, 007 publicly available images, analyzed by 6, 283 annotators who were asked to indicate and explain how and why they felt in a particular way when observing a specific image, producing a total of 526, 749 responses.
1 code implementation • 22 Sep 2022 • Geng Yuan, Yanyu Li, Sheng Li, Zhenglun Kong, Sergey Tulyakov, Xulong Tang, Yanzhi Wang, Jian Ren
Therefore, we analyze the feasibility and potentiality of using the layer freezing technique in sparse training and find it has the potential to save considerable training costs.
no code implementations • 24 Jul 2022 • Zezhou Cheng, Menglei Chai, Jian Ren, Hsin-Ying Lee, Kyle Olszewski, Zeng Huang, Subhransu Maji, Sergey Tulyakov
In this paper, we propose a generic multi-modal generative model that couples the 2D modalities and implicit 3D representations through shared latent spaces.
1 code implementation • 21 Jun 2022 • Ivan Skorokhodov, Sergey Tulyakov, Yiqun Wang, Peter Wonka
In this work, we show that it is possible to obtain a high-resolution 3D generator with SotA image quality by following a completely different route of simply training the model patch-wise.
1 code implementation • 15 Jun 2022 • Ye Zhu, Yu Wu, Kyle Olszewski, Jian Ren, Sergey Tulyakov, Yan Yan
To this end, we introduce a Conditional Discrete Contrastive Diffusion (CDCD) loss and design two contrastive diffusion mechanisms to effectively incorporate it into the denoising process.
4 code implementations • 2 Jun 2022 • Yanyu Li, Geng Yuan, Yang Wen, Ju Hu, Georgios Evangelidis, Sergey Tulyakov, Yanzhi Wang, Jian Ren
Our work proves that properly designed transformers can reach extremely low latency on mobile devices while maintaining high performance.
no code implementations • 22 Apr 2022 • Verica Lazova, Vladimir Guzov, Kyle Olszewski, Sergey Tulyakov, Gerard Pons-Moll
With the aim of obtaining interpretable and controllable scene representations, our model couples learnt scene-specific feature volumes with a scene agnostic neural rendering network.
1 code implementation • 1 Apr 2022 • Ye Zhu, Kyle Olszewski, Yu Wu, Panos Achlioptas, Menglei Chai, Yan Yan, Sergey Tulyakov
We present Dance2Music-GAN (D2M-GAN), a novel adversarial multi-modal framework that generates complex musical samples conditioned on dance videos.
1 code implementation • 31 Mar 2022 • Huan Wang, Jian Ren, Zeng Huang, Kyle Olszewski, Menglei Chai, Yun Fu, Sergey Tulyakov
On the other hand, Neural Light Field (NeLF) presents a more straightforward representation over NeRF in novel view synthesis -- the rendering of a pixel amounts to one single forward pass without ray-marching.
1 code implementation • CVPR 2022 • Ligong Han, Jian Ren, Hsin-Ying Lee, Francesco Barbieri, Kyle Olszewski, Shervin Minaee, Dimitris Metaxas, Sergey Tulyakov
In addition, our model can extract visual information as suggested by the text prompt, e. g., "an object in image one is moving northeast", and generate corresponding videos.
1 code implementation • CVPR 2022 • Willi Menapace, Stéphane Lathuilière, Aliaksandr Siarohin, Christian Theobalt, Sergey Tulyakov, Vladislav Golyanik, Elisa Ricci
We present Playable Environments - a new representation for interactive video generation and manipulation in space and time.
1 code implementation • ICLR 2022 • Qing Jin, Jian Ren, Richard Zhuang, Sumant Hanumante, Zhengang Li, Zhiyu Chen, Yanzhi Wang, Kaiyuan Yang, Sergey Tulyakov
Our approach achieves comparable and better performance, when compared not only to existing quantization techniques with INT32 multiplication or floating-point arithmetic, but also to the full-precision counterparts, achieving state-of-the-art performance.
1 code implementation • 7 Jan 2022 • Zhengfei Kuang, Kyle Olszewski, Menglei Chai, Zeng Huang, Panos Achlioptas, Sergey Tulyakov
We present a novel method to acquire object representations from online image collections, capturing high-quality geometry and material properties of arbitrary objects from photographs with varying cameras, illumination, and backgrounds.
no code implementations • CVPR 2022 • Yen-Chi Cheng, Chieh Hubert Lin, Hsin-Ying Lee, Jian Ren, Sergey Tulyakov, Ming-Hsuan Yang
Existing image outpainting methods pose the problem as a conditional image-to-image translation task, often generating repetitive structures and textures by replicating the content available in the input image.
1 code implementation • CVPR 2022 • Ivan Skorokhodov, Sergey Tulyakov, Mohamed Elhoseiny
We build our model on top of StyleGAN2 and it is just ${\approx}5\%$ more expensive to train at the same resolution while achieving almost the same image quality.
no code implementations • CVPR 2021 • Jian Ren, Menglei Chai, Oliver J. Woodford, Kyle Olszewski, Sergey Tulyakov
Human motion retargeting aims to transfer the motion of one person in a "driving" video or set of images to another person.
1 code implementation • ICLR 2021 • Yu Tian, Jian Ren, Menglei Chai, Kyle Olszewski, Xi Peng, Dimitris N. Metaxas, Sergey Tulyakov
We introduce a motion generator that discovers the desired trajectory, in which content and motion are disentangled.
2 code implementations • CVPR 2021 • Aliaksandr Siarohin, Oliver J. Woodford, Jian Ren, Menglei Chai, Sergey Tulyakov
To facilitate animation and prevent the leakage of the shape of the driving object, we disentangle shape and pose of objects in the region space.
Ranked #1 on
Video Reconstruction
on Tai-Chi-HD (512)
no code implementations • ICLR 2022 • Chieh Hubert Lin, Hsin-Ying Lee, Yen-Chi Cheng, Sergey Tulyakov, Ming-Hsuan Yang
We present a novel framework, InfinityGAN, for arbitrary-sized image generation.
no code implementations • 1 Apr 2021 • Yen-Chi Cheng, Chieh Hubert Lin, Hsin-Ying Lee, Jian Ren, Sergey Tulyakov, Ming-Hsuan Yang
Existing image outpainting methods pose the problem as a conditional image-to-image translation task, often generating repetitive structures and textures by replicating the content available in the input image.
1 code implementation • 9 Mar 2021 • Mengmeng Ma, Jian Ren, Long Zhao, Sergey Tulyakov, Cathy Wu, Xi Peng
A common assumption in multimodal learning is the completeness of training data, i. e., full modalities are available in all training examples.
1 code implementation • CVPR 2021 • Qing Jin, Jian Ren, Oliver J. Woodford, Jiazhuo Wang, Geng Yuan, Yanzhi Wang, Sergey Tulyakov
In this work, we aim to address these issues by introducing a teacher network that provides a search space in which efficient network architectures can be found, in addition to performing knowledge distillation.
1 code implementation • CVPR 2021 • Willi Menapace, Stéphane Lathuilière, Sergey Tulyakov, Aliaksandr Siarohin, Elisa Ricci
This paper introduces the unsupervised learning problem of playable video generation (PVG).
1 code implementation • 30 Oct 2020 • Zhentao Tan, Menglei Chai, Dongdong Chen, Jing Liao, Qi Chu, Lu Yuan, Sergey Tulyakov, Nenghai Yu
In this paper, we present MichiGAN (Multi-Input-Conditioned Hair Image GAN), a novel conditional image generation method for interactive portrait hair manipulation.
2 code implementations • 29 Apr 2020 • Ondřej Texler, David Futschik, Michal Kučera, Ondřej Jamriška, Šárka Sochorová, Menglei Chai, Sergey Tulyakov, Daniel Sýkora
In this paper, we present a learning-based method to the keyframe-based video stylization that allows an artist to propagate the style from a few selected keyframes to the rest of the sequence.
no code implementations • ECCV 2020 • Menglei Chai, Jian Ren, Sergey Tulyakov
Unlike existing supervised translation methods that require model-level similarity to preserve consistent structure representation for both real images and fake renderings, our method adopts an unsupervised solution to work on arbitrary hair models.
no code implementations • 7 Apr 2020 • Jian Ren, Menglei Chai, Sergey Tulyakov, Chen Fang, Xiaohui Shen, Jianchao Yang
In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video.
2 code implementations • 7 Apr 2020 • Aliaksandr Siarohin, Subhankar Roy, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe
To overcome this limitation, we propose a self-supervised deep learning method for co-part segmentation.
2 code implementations • NeurIPS 2019 • Aliaksandr Siarohin, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe
To achieve this, we decouple appearance and motion information using a self-supervised formulation.
Ranked #1 on
Video Reconstruction
on Tai-Chi-HD
no code implementations • 16 Aug 2019 • Zhizhong Li, Linjie Luo, Sergey Tulyakov, Qieyun Dai, Derek Hoiem
Our key idea to improve domain adaptation is to introduce a separate anchor task (such as facial landmarks) whose annotations can be obtained at no cost or are already available on both synthetic and real datasets.
1 code implementation • ICCV 2019 • Kyle Olszewski, Sergey Tulyakov, Oliver Woodford, Hao Li, Linjie Luo
We propose a novel approach to performing fine-grained 3D manipulation of image content via a convolutional neural network, which we call the Transformable Bottleneck Network (TBN).
no code implementations • NAACL 2019 • Lahari Poddar, Leonardo Neves, William Brendel, Luis Marujo, Sergey Tulyakov, Pradeep Karuturi
Leveraging the assumption that learning the topic of a bug is a sub-task for detecting duplicates, we design a loss function that can jointly perform both tasks but needs supervision for only duplicate classification, achieving topic clustering in an unsupervised fashion.
no code implementations • CVPR 2019 • Zhenglin Geng, Chen Cao, Sergey Tulyakov
This is achieved by first fitting a 3D face model and then disentangling the face into a texture and a shape.
1 code implementation • CVPR 2019 • Aliaksandr Siarohin, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe
This is achieved through a deep architecture that decouples appearance and motion information.
no code implementations • 30 Nov 2017 • Sergey Tulyakov, Andrew Fitzgibbon, Sebastian Nowozin
We show that such a combination is beneficial because the unlabeled data acts as a data-driven form of regularization, allowing generative models trained on few labeled samples to reach the performance of fully-supervised generative models trained on much larger datasets.
5 code implementations • CVPR 2018 • Sergey Tulyakov, Ming-Yu Liu, Xiaodong Yang, Jan Kautz
The proposed framework generates a video by mapping a sequence of random vectors to a sequence of video frames.
no code implementations • CVPR 2016 • Sergey Tulyakov, Xavier Alameda-Pineda, Elisa Ricci, Lijun Yin, Jeffrey F. Cohn, Nicu Sebe
Recent studies in computer vision have shown that, while practically invisible to a human observer, skin color changes due to blood flow can be captured on face videos and, surprisingly, be used to estimate the heart rate (HR).
no code implementations • ICCV 2015 • Sergey Tulyakov, Nicu Sebe
To support the ability of our method to reliably reconstruct 3D shapes, we introduce a simple method for head pose estimation using a single image that reaches higher accuracy than the state of the art.