Search Results for author: Tien-Tsin Wong

Found 20 papers, 10 papers with code

Improved Diffusion-based Image Colorization via Piggybacked Models

no code implementations21 Apr 2023 Hanyuan Liu, Jinbo Xing, Minshan Xie, Chengze Li, Tien-Tsin Wong

Our key idea is to exploit the color prior knowledge in the pre-trained T2I diffusion model for realistic and diverse colorization.

Colorization Image Colorization

CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior

1 code implementation CVPR 2023 Jinbo Xing, Menghan Xia, Yuechen Zhang, Xiaodong Cun, Jue Wang, Tien-Tsin Wong

In this paper, we propose to cast speech-driven facial animation as a code query task in a finite proxy space of the learned codebook, which effectively promotes the vividness of the generated motions by reducing the cross-modal mapping uncertainty.

3D Face Animation regression

Pseudo Bias-Balanced Learning for Debiased Chest X-ray Classification

1 code implementation18 Mar 2022 Luyang Luo, Dunyuan Xu, Hao Chen, Tien-Tsin Wong, Pheng-Ann Heng

Deep learning models were frequently reported to learn from shortcuts like dataset biases.

Screentone-Preserved Manga Retargeting

no code implementations7 Mar 2022 Minshan Xie, Menghan Xia, Xueting Liu, Tien-Tsin Wong

Fortunately, the rescaled manga shares the same region-wise screentone correspondences with the original manga, which enables us to simplify the screentone synthesis problem as an anchor-based proposals selection and rearrangement problem.


Point Set Self-Embedding

1 code implementation28 Feb 2022 Ruihui Li, Xianzhi Li, Tien-Tsin Wong, Chi-Wing Fu

To achieve a learnable self-embedding scheme, we design a novel framework with two jointly-trained networks: one to encode the input point set into its self-embedded sparse point set and the other to leverage the embedded information for inverting the original point set back.

Scale-arbitrary Invertible Image Downscaling

no code implementations29 Jan 2022 Jinbo Xing, WenBo Hu, Tien-Tsin Wong

In this paper, we propose a scale-Arbitrary Invertible image Downscaling Network (AIDN), to natively downscale HR images with arbitrary scale factors.


Neural Recognition of Dashed Curves With Gestalt Law of Continuity

no code implementations CVPR 2022 Hanyuan Liu, Chengze Li, Xueting Liu, Tien-Tsin Wong

While humans can intuitively recognize dashed curves from disjoint curve segments based on the law of continuity in Gestalt psychology, it is extremely difficult for computers to model the Gestalt law of continuity and recognize the dashed curves since high-level semantic understanding is needed for this task.

Invertible Tone Mapping with Selectable Styles

no code implementations9 Oct 2021 Zhuming Zhang, Menghan Xia, Xueting Liu, Chengze Li, Tien-Tsin Wong

In this paper, we propose an invertible tone mapping method that converts the multi-exposure HDR to a true LDR (8-bit per color channel) and reserves the capability to accurately restore the original HDR from this {\em invertible LDR}.

Tone Mapping

Conditional Directed Graph Convolution for 3D Human Pose Estimation

1 code implementation16 Jul 2021 WenBo Hu, Changgong Zhang, Fangneng Zhan, Lei Zhang, Tien-Tsin Wong

Based on this representation, we further propose a spatial-temporal conditional directed graph convolution to leverage varying non-local dependence for different poses by conditioning the graph topology on input poses.

3D Human Pose Estimation

User-Guided Line Art Flat Filling With Split Filling Mechanism

no code implementations CVPR 2021 Lvmin Zhang, Chengze Li, Edgar Simo-Serra, Yi Ji, Tien-Tsin Wong, Chunping Liu

We present a deep learning framework for user-guided line art flat filling that can compute the "influence areas" of the user color scribbles, i. e., the areas where the user scribbles should propagate and influence.

Exploiting Aliasing for Manga Restoration

1 code implementation CVPR 2021 Minshan Xie, Menghan Xia, Tien-Tsin Wong

First, we predict the target resolution from the degraded manga via the Scale Estimation Network (SE-Net) with spatial voting scheme.

Bidirectional Projection Network for Cross Dimension Scene Understanding

1 code implementation CVPR 2021 WenBo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong

Via the \emph{BPM}, complementary 2D and 3D information can interact with each other in multiple architectural levels, such that advantages in these two visual domains can be combined for better scene recognition.

2D Semantic Segmentation 3D Semantic Segmentation +3

A Learned Compact and Editable Light Field Representation

no code implementations21 Mar 2021 Menghan Xia, Jose Echevarria, Minshan Xie, Tien-Tsin Wong

Light fields are 4D scene representation typically structured as arrays of views, or several directional samples per pixel in a single view.

Deep Halftoning With Reversible Binary Pattern

1 code implementation ICCV 2021 Menghan Xia, WenBo Hu, Xueting Liu, Tien-Tsin Wong

Existing halftoning algorithms usually drop colors and fine details when dithering color images with binary dot patterns, which makes it extremely difficult to recover the original information.

Enhance Convolutional Neural Networks with Noise Incentive Block

no code implementations9 Dec 2020 Menghan Xia, Yi Wang, Chu Han, Tien-Tsin Wong

Noise Incentive Block (NIB), which serves as a generic plug-in for any CNN generation model.

Image Generation Translation

Mononizing Binocular Videos

1 code implementation3 Sep 2020 Wenbo Hu, Menghan Xia, Chi-Wing Fu, Tien-Tsin Wong

This paper presents the idea ofmono-nizingbinocular videos and a frame-work to effectively realize it.

Image and Video Processing Graphics

Binocular Tone Mapping with Improved Overall Contrast and Local Details

no code implementations17 Sep 2018 Zhuming Zhang, Xinghong Hu, Xueting Liu, Tien-Tsin Wong

However, the existing research lacks the binocular perception study and is unable to generate the optimal binocular pair that presents the most visual content.

Tone Mapping

Real-time Deep Video Deinterlacing

2 code implementations1 Aug 2017 Haichao Zhu, Xueting Liu, Xiangyu Mao, Tien-Tsin Wong

Interlacing is a widely used technique, for television broadcast and video recording, to double the perceived frame rate without increasing the bandwidth.

Super-Resolution Translation +1

ENFT: Efficient Non-Consecutive Feature Tracking for Robust Structure-from-Motion

3 code implementations27 Oct 2015 Guofeng Zhang, Hao-Min Liu, Zilong Dong, Jiaya Jia, Tien-Tsin Wong, Hujun Bao

Our framework consists of steps of solving the feature `dropout' problem when indistinctive structures, noise or large image distortion exists, and of rapidly recognizing and joining common features located in different subsequences.

Cannot find the paper you are looking for? You can Submit a new open access paper.