Papers › Face Hallucination via Split-Attention in Split-Attention Network

Face Hallucination via Split-Attention in Split-Attention Network

22 Oct 2020arXiv:2010.11575archive 2025-07-28

Tao Lu, Yuanzhi Wang, Yanduo Zhang, Yu Wang, Wei Liu, Zhongyuan Wang, Junjun Jiang

Recently, convolutional neural networks (CNNs) have been widely employed to promote the face hallucination due to the ability to predict high-frequency details from a large number of samples. However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e.g., face detection, facial recognition). To tackle this issue, we propose a novel external-internal split attention group (ESAG), which encompasses two paths responsible for facial structure information and facial texture details, respectively. By fusing the features from these two paths, the consistency of facial structure and the fidelity of facial details are strengthened at the same time. Then, we propose a split-attention in split-attention network (SISN) to reconstruct photorealistic high-resolution facial images by cascading several ESAGs. Experimental results on face hallucination and face recognition unveil that the proposed method not only significantly improves the clarity of hallucinated faces, but also encourages the subsequent face recognition performance substantially. Codes have been released at https://github.com/mdswyz/SISN-Face-Hallucination.

PaperPDFCode

Code

mdswyz/SISN-Face-Hallucination officialmentioned in papermentioned on GitHubpytorch 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

Face DetectionFace HallucinationFace RecognitionHallucinationImage ReconstructionSuper-Resolution

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Average PoolingBatch NormalizationDense ConnectionsGlobal Average PoolingReLUResidual ConnectionSoftmaxSplit Attention

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