1 code implementation • 29 Nov 2023 • Eric Hedlin, Gopal Sharma, Shweta Mahajan, Xingzhe He, Hossam Isack, Abhishek Kar Helge Rhodin, Andrea Tagliasacchi, Kwang Moo Yi
Unsupervised learning of keypoints and landmarks has seen significant progress with the help of modern neural network architectures, but performance is yet to match the supervised counterpart, making their practicability questionable.
Ranked #1 on Unsupervised Human Pose Estimation on Tai-Chi-HD
no code implementations • 7 Nov 2023 • Xingzhe He, Zhiwen Cao, Nicholas Kolkin, Lantao Yu, Kun Wan, Helge Rhodin, Ratheesh Kalarot
This strategy enables the model to preserve fine details of the desired subjects, such as text and logos.
no code implementations • CVPR 2023 • Xingzhe He, Gaurav Bharaj, David Ferman, Helge Rhodin, Pablo Garrido
Supervised keypoint localization methods rely on large manually labeled image datasets, where objects can deform, articulate, or occlude.
no code implementations • 10 Mar 2023 • Ziqian Wu, Xingzhe He, Yijun Li, Cheng Yang, Rui Liu, Shiying Xiong, Bo Zhu
We present a lightweighted neural PDE representation to discover the hidden structure and predict the solution of different nonlinear PDEs.
1 code implementation • 21 May 2022 • Xingzhe He, Bastian Wandt, Helge Rhodin
Our key ingredients are i) an encoder that predicts keypoint locations in an input image, ii) a shared graph as a latent variable that links the same pairs of keypoints in every image, iii) an intermediate edge map that combines the latent graph edge weights and keypoint locations in a soft, differentiable manner, and iv) an inpainting objective on randomly masked images.
Ranked #1 on Unsupervised Landmark Detection on MAFL Unaligned
no code implementations • 6 May 2022 • Xingzhe He, Bastian Wandt, Helge Rhodin
Generative adversarial networks (GANs) can now generate photo-realistic images.
1 code implementation • CVPR 2022 • Xingzhe He, Bastian Wandt, Helge Rhodin
Segmenting an image into its parts is a frequent preprocess for high-level vision tasks such as image editing.
1 code implementation • 29 Mar 2021 • Xingzhe He, Bastian Wandt, Helge Rhodin
Generative adversarial networks (GANs) have attained photo-realistic quality in image generation.
Ranked #5 on Unsupervised Keypoint Estimation on CUB
no code implementations • 1 Jan 2021 • Shiying Xiong, Xingzhe He, Yunjin Tong, Yitong Deng, Bo Zhu
Since the number of such vortices are much smaller than that of the Eulerian, grid discretization, this Lagrangian discretization in essence encodes the system dynamics on a compact physics-based latent space.
no code implementations • ICLR 2021 • Shiying Xiong, Yunjin Tong, Xingzhe He, Shuqi Yang, Cheng Yang, Bo Zhu
The enabling mechanics of our approach is an augmented symplectic time integrator to decouple the position and momentum energy terms and facilitate their evolution.
1 code implementation • NeurIPS 2020 • Shuqi Yang, Xingzhe He, Bo Zhu
A neural projection operator lies at the heart of our approach, composed of a lightweight network with an embedded recursive architecture that interactively enforces learned underpinning constraints and predicts the various governed behaviors of different physical systems.
no code implementations • 7 Jun 2020 • Shiying Xiong, Xingzhe He, Yunjin Tong, Runze Liu, Bo Zhu
The ability of our model to predict long-term discontinuity from a short window of continuous training data is in general considered impossible using traditional machine learning approaches.
no code implementations • 7 Jun 2020 • Shiying Xiong, Xingzhe He, Yunjin Tong, Yitong Deng, Bo Zhu
To tackle this challenge, we propose a novel learning-based framework, the Neural Vortex Method (NVM), which builds a neural-network description of the Lagrangian vortex structures and their interaction dynamics to reconstruct the high-resolution Eulerian flow field in a physically-precise manner.
1 code implementation • 11 May 2020 • Yunjin Tong, Shiying Xiong, Xingzhe He, Guanghan Pan, Bo Zhu
We propose an effective and lightweight learning algorithm, Symplectic Taylor Neural Networks (Taylor-nets), to conduct continuous, long-term predictions of a complex Hamiltonian dynamic system based on sparse, short-term observations.
1 code implementation • ICLR 2020 • Xingzhe He, Helen Lu Cao, Bo Zhu
This paper presents a novel physics-inspired deep learning approach for point cloud processing motivated by the natural flow phenomena in fluid mechanics.