508 citations · 2.4k across the 113 of their papers we have counts for
10 papers · 1 filter
Context-Aware Synthesis and Placement of Object Instances
Donghoon Lee, Sifei Liu, Jinwei Gu +3
Learning to insert an object instance into an image in a semantically coherent manner is a challenging and interesting problem. Solving it requires (a) determining a location to pl…
Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
Deqing Sun, Xiaodong Yang, Ming-Yu Liu +1
We investigate two crucial and closely related aspects of CNNs for optical flow estimation: models and training. First, we design a compact but effective CNN model, called PWC-Net,…
Unsupervised Stylish Image Description Generation via Domain Layer Norm
Cheng Kuan Chen, Zhu Feng Pan, Min Sun +1
Most of the existing works on image description focus on generating expressive descriptions. The only few works that are dedicated to generating stylish (e.g., romantic, lyric, etc…
Video-to-Video Synthesis
Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu +4
We study the problem of video-to-video synthesis, whose goal is to learn a mapping function from an input source video (e.g., a sequence of semantic segmentation masks) to an outpu…
Superpixel Sampling Networks
Varun Jampani, Deqing Sun, Ming-Yu Liu +2
Superpixels provide an efficient low/mid-level representation of image data, which greatly reduces the number of image primitives for subsequent vision tasks. Existing superpixel a…
Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation
Aysegul Dundar, Ming-Yu Liu, Ting-Chun Wang +2
Deep neural networks have largely failed to effectively utilize synthetic data when applied to real images due to the covariate shift problem. In this paper, we show that by applyi…
Multimodal Unsupervised Image-to-Image Translation
Xun Huang, Ming-Yu Liu, Serge Belongie +1
Unsupervised image-to-image translation is an important and challenging problem in computer vision. Given an image in the source domain, the goal is to learn the conditional distri…
A Closed-form Solution to Photorealistic Image Stylization
Yijun Li, Ming-Yu Liu, Xueting Li +2
Photorealistic image stylization concerns transferring style of a reference photo to a content photo with the constraint that the stylized photo should remain photorealistic. While…
Localization-Aware Active Learning for Object Detection
Chieh-Chi Kao, Teng-Yok Lee, Pradeep Sen +1
Active learning - a class of algorithms that iteratively searches for the most informative samples to include in a training dataset - has been shown to be effective at annotating d…
Reblur2Deblur: Deblurring Videos via Self-Supervised Learning
Huaijin Chen, Jinwei Gu, Orazio Gallo +3
Motion blur is a fundamental problem in computer vision as it impacts image quality and hinders inference. Traditional deblurring algorithms leverage the physics of the image forma…