Papers › Demystifying Neural Style Transfer

Demystifying Neural Style Transfer

4 Jan 2017arXiv:1701.01036archive 2025-07-28

Yanghao Li, Naiyan Wang, Jiaying Liu, Xiaodi Hou

Neural Style Transfer has recently demonstrated very exciting results which catches eyes in both academia and industry. Despite the amazing results, the principle of neural style transfer, especially why the Gram matrices could represent style remains unclear. In this paper, we propose a novel interpretation of neural style transfer by treating it as a domain adaptation problem. Specifically, we theoretically show that matching the Gram matrices of feature maps is equivalent to minimize the Maximum Mean Discrepancy (MMD) with the second order polynomial kernel. Thus, we argue that the essence of neural style transfer is to match the feature distributions between the style images and the generated images. To further support our standpoint, we experiment with several other distribution alignment methods, and achieve appealing results. We believe this novel interpretation connects these two important research fields, and could enlighten future researches.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

aryan-mann/style-transfer mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Neural Algorithm of Artistic Style (arXiv:1508.06576; that paper's own run record: 76 ran (of which 0 constructed an object rather than computing a result; 44 with no instrument failure: 7 honoured, 3 violated, 34 with no contract checked; 32 where Syntology's instrument failed) · 34 unverified); nothing checks that they implement this paper's method. report
sanjayjonckheere/iN_iS_Tee_One mentioned on GitHubtfSyntology: not harvested report
sonnguyen129/deep-feature-rotation tfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer (arXiv:2108.07379; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Domain AdaptationStyle Transfer

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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