Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks

Abstract

Convolutional neural networks have recently demonstrated high-quality reconstruction for single image super-resolution. However, existing methods often require a large number of network parameters and entail heavy computational loads at runtime for generating high-accuracy super-resolution results. In this paper, we propose the deep Laplacian Pyramid Super-Resolution Network for fast and accurate image super-resolution. The proposed network progressively reconstructs the sub-band residuals of high-resolution images at multiple pyramid levels. In contrast to existing methods that involve the bicubic interpolation for pre-processing (which results in large feature maps), the proposed method directly extracts features from the low-resolution input space and thereby entails low computational loads. We train the proposed network with deep supervision using the robust Charbonnier loss functions and achieve high-quality image reconstruction. Furthermore, we utilize the recursive layers to share parameters across as well as within pyramid levels, and thus drastically reduce the number of parameters. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of run-time and image quality.

Self-Supervised Learning of Class Embeddings from Video

“…(c) Illustration of how the predicted M r at each resolution Rr are used to determine the warp A r . hierarchical manner has been found to be useful in a number of tasks [9,27,28,50,51]. In our case, the network learns to determine roughly how to transform points (e.g.…”

Adaptive Densely Connected Single Image Super-Resolution

“…As can be seen from the table, the PSNR and SSIM of the algorithm in ×2, ×3, ×4 exceed the current state of the art. Figure 6 show the Qualitative comparison of our models with Bicubic, SRCNN [5], VDSR [10], LapSRN [12], MSLapSRN [13], EDSR [16], RCAN [31], and SAN [4] . The images of SRCNN, EDSR, and RCAN are derived from the author's open-source model and code.…”

HRAN: Hybrid Residual Attention Network for Single Image Super-Resolution

“…In this section, we compare our qualitative results with the state-of-the-art methods: SRCNN [3], SPMSR [21], FS-RCNN [4], VDSR [10], IRCNN [38], SRMDNF [39], SCN [34], DRRN [27], LapSRN [12], MSLapSRN [13], Enet-PAT [22], MemNet [28], and EDSR [17].…”

“…SRCNN [3] FSRCNN [4] SCN [34] VDSR [10] DRRN [27] LapSRN [12] MSLapSRN [13] ENet-PAT [22] MemNet [28] EDSR [17] SRMDNF [39] HRAN (ours) Figure 6. "img 074" from Urban100 (4×): State-of-the-art results with Bicubic (BI) degradation.…”