Jun-Yan Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jun-Yan Zhu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Antonio Torralba
Massachusetts Institute of Technology
1 shared publication - Bolei Zhou
University of California, Los Angeles, CA, USA
1 shared publication David Bau
MIT CSAIL and MIT IBM Watson AI Lab MIT CSAIL JONAS WULFF MIT HENDRIK STROBELT IBM Research and MIT IBM Watson AI Lab MIT CSAIL BOLEI ZHOU The Chinese University of Hong Kong CSAIL ANTONIO TORRALBA MIT CSAIL and MIT
1 shared publication- Hendrik Strobelt1 shared publication
- Jonas Wulff
MIT CSAIL MIT CSAIL MIT CSAIL MIT CSAIL MIT CSAIL
1 shared publication William Peebles
MIT CSAIL and MIT IBM Watson AI Lab MIT CSAIL JONAS WULFF MIT HENDRIK STROBELT IBM Research and MIT IBM Watson AI Lab MIT CSAIL BOLEI ZHOU The Chinese University of Hong Kong CSAIL ANTONIO TORRALBA MIT CSAIL and MIT
1 shared publication
Latest Publications
- Open Access
Semantic Photo Manipulation with a Generative Image Prior
Despite the recent success of GANs in synthesizing images conditioned on inputs such as a user sketch, text, or semantic labels, manipulating the high-level attributes of an existing natural photograph with GANs is challenging for two reasons. First, it is hard for GANs to precisely reproduce an input image. Second, after manipulation, the newly synthesized pixels often do not fit the original image. In this paper, we address these issues by adapting the image prior learned by GANs to image statistics of an individual image. Our method can accurately reconstruct the input image and synthesize new content, consistent with the appearance of the input image. We demonstrate our interactive system on several semantic image editing tasks, including synthesizing new objects consistent with background, removing unwanted objects, and changing the appearance of an object. Quantitative and qualitative comparisons against several existing methods demonstrate the effectiveness of our method.
Open AccessSemantic Photo Manipulation with a Generative Image Prior
Despite the recent success of GANs in synthesizing images conditioned on inputs such as a user sketch, text, or semantic labels, manipulating the high-level attributes of an existing natural photograph with GANs is challenging for two reasons. First, it is hard for GANs to precisely reproduce an input image. Second, after manipulation, the newly synthesized pixels often do not fit the original image. In this paper, we address these issues by adapting the image prior learned by GANs to image statistics of an individual image. Our method can accurately reconstruct the input image and synthesize new content, consistent with the appearance of the input image. We demonstrate our interactive system on several semantic image editing tasks, including synthesizing new objects consistent with background, removing unwanted objects, and changing the appearance of an object. Quantitative and qualitative comparisons against several existing methods demonstrate the effectiveness of our method.