Papers › Deep Network Interpolation for Continuous Imagery Effect Transition

Deep Network Interpolation for Continuous Imagery Effect Transition

26 Nov 2018CVPR 2019 6arXiv:1811.10515archive 2025-07-28

Xintao Wang, Ke Yu, Chao Dong, Xiaoou Tang, Chen Change Loy

Deep convolutional neural network has demonstrated its capability of learning a deterministic mapping for the desired imagery effect. However, the large variety of user flavors motivates the possibility of continuous transition among different output effects. Unlike existing methods that require a specific design to achieve one particular transition (e.g., style transfer), we propose a simple yet universal approach to attain a smooth control of diverse imagery effects in many low-level vision tasks, including image restoration, image-to-image translation, and style transfer. Specifically, our method, namely Deep Network Interpolation (DNI), applies linear interpolation in the parameter space of two or more correlated networks. A smooth control of imagery effects can be achieved by tweaking the interpolation coefficients. In addition to DNI and its broad applications, we also investigate the mechanism of network interpolation from the perspective of learned filters.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

kzkymur/transition mentioned on GitHubpytorch report
S-aiueo32/dni-demo pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image RestorationImage-to-Image TranslationStyle TransferTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Tunable Network

Tunable Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections