mlsanityData to 14 Oct 2026

Continuous Facial Motion Deblurring

arXiv 2207.06626 ↗First posted 14 Jul 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce a novel framework for continuous facial motion deblurring that restores the continuous sharp moment latent in a single motion-blurred face image via a moment control factor. Although a motion-blurred image is the accumulated signal of continuous sharp moments during the exposure time, most existing single image deblurring approaches aim to restore a fixed number of frames using multiple networks and training stages. To address this problem, we propose a continuous facial motion deblurring network based on GAN (CFMD-GAN), which is a novel framework for restoring the continuous moment latent in a single motion-blurred face image with a single network and a single training stage. To stabilize the network training, we train the generator to restore continuous moments in the order determined by our facial motion-based reordering process (FMR) utilizing domain-specific knowledge of the face. Moreover, we propose an auxiliary regressor that helps our generator produce more accurate images by estimating continuous sharp moments. Furthermore, we introduce a control-adaptive (ContAda) block that performs spatially deformable convolution and channel-wise attention as a function of the control factor. Extensive experiments on the 300VW datasets demonstrate that the proposed framework generates a various number of continuous output frames by varying the moment control factor. Compared with the recent single-to-single image deblurring networks trained with the same 300VW training set, the proposed method show the superior performance in restoring the central sharp frame in terms of perceptual metrics, including LPIPS, FID and Arcface identity distance. The proposed method outperforms the existing single-to-video deblurring method for both qualitative and quantitative comparisons.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 62 of its 94 references that are in the map. First posted on arXiv 14 Jul 2022.

Builds on

62 of 94 references.

References · 62

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  7. 2022Generative Adversarial Networkscited by 5,627
  8. 2017Squeeze-and-Excitation Networkscited by 4,789
  9. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  11. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  12. 2014Conditional Generative Adversarial Netscited by 2,162
38 more
  1. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  2. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  3. 2017Deformable Convolutional Networkscited by 1,488
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  5. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  6. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  7. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
  8. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  9. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 903
  10. 2021Multi-Stage Progressive Image Restorationcited by 816
  11. 2018Self-Attention Generative Adversarial Networkscited by 809
  12. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 727
  13. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 695
  14. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 670
  15. 2020GANSpace: Discovering Interpretable GAN Controlscited by 614
  16. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  17. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 494
  18. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  19. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 349
  20. 2018Scale-recurrent Network for Deep Image Deblurringcited by 333
  21. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 326
  22. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 285
  23. 2018cGANs with Projection Discriminatorcited by 254
  24. 2016SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioningcited by 219
  25. 2019Deep Stacked Hierarchical Multi-patch Network for Image Deblurringcited by 206
  26. 2020Human-Aware Motion Deblurringcited by 175
  27. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  28. 2018The 2018 PIRM Challenge on Perceptual Image Super-resolutioncited by 156
  29. 2015Learning a Convolutional Neural Network for Non-uniform Motion Blur Removalcited by 149
  30. 2020A U-Net Based Discriminator for Generative Adversarial Networkscited by 128
  31. 2019Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Trainingcited by 112
  32. 2016From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blurcited by 81
  33. 2018Deep Semantic Face Deblurringcited by 80
  34. 2016A Neural Approach to Blind Motion Deblurringcited by 69
  35. 2018Learning to Extract a Video Sequence from a Single Motion-Blurred Imagecited by 57
  36. 2021Rebooting ACGAN: Auxiliary Classifier GANs with Stable Trainingcited by 57
  37. 2016From Facial Expression Recognition to Interpersonal Relation Predictioncited by 53
  38. 2018Bringing Alive Blurred Momentscited by 45

50 most cited of 62 All 62 (JSON)

Built on by

Not cited yet.