Simple Baselines for Image Restoration
- URL: http://arxiv.org/abs/2204.04676v1
- Date: Sun, 10 Apr 2022 12:48:38 GMT
- Title: Simple Baselines for Image Restoration
- Authors: Liangyu Chen, Xiaojie Chu, Xiangyu Zhang, Jian Sun
- Abstract summary: We propose a simple baseline that exceeds the state-of-the-art (SOTA) methods and is computationally efficient.
We derive a Activation Free Network, namely NAFNet, from the baseline.
SOTA results are achieved on various challenging benchmarks, e.g. 33.69 dB PSNR on GoPro (for image deblurring), exceeding the previous SOTA 0.38 dB with only 8.4% of its computational costs; 40.30 dB PSNR on SIDD (for image denoising), exceeding the previous SOTA 0.28 dB with less than half of its computational costs.
- Score: 79.48718779396971
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Although there have been significant advances in the field of image
restoration recently, the system complexity of the state-of-the-art (SOTA)
methods is increasing as well, which may hinder the convenient analysis and
comparison of methods. In this paper, we propose a simple baseline that exceeds
the SOTA methods and is computationally efficient. To further simplify the
baseline, we reveal that the nonlinear activation functions, e.g. Sigmoid,
ReLU, GELU, Softmax, etc. are not necessary: they could be replaced by
multiplication or removed. Thus, we derive a Nonlinear Activation Free Network,
namely NAFNet, from the baseline. SOTA results are achieved on various
challenging benchmarks, e.g. 33.69 dB PSNR on GoPro (for image deblurring),
exceeding the previous SOTA 0.38 dB with only 8.4% of its computational costs;
40.30 dB PSNR on SIDD (for image denoising), exceeding the previous SOTA 0.28
dB with less than half of its computational costs. The code and the pretrained
models will be released at https://github.com/megvii-research/NAFNet.
Related papers
- Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies [19.100334346597982]
We analyze how model size, dataset size, and synthetic data quality affect robustness by developing the first scaling laws for adversarial training.
Our scaling laws reveal inefficiencies in prior art and provide actionable feedback to advance the field.
arXiv Detail & Related papers (2024-04-14T20:14:38Z) - ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation [5.179738379203527]
In absence of parallax cues, a learning-based single image depth estimation model relies heavily on shading and contextual cues in the image.
It is necessary to train such models on large and varied datasets, which are difficult to capture.
Using embeddings from pre-trained foundational models, such as CLIP, improves zero shot transfer in several applications.
arXiv Detail & Related papers (2024-03-27T17:53:30Z) - ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models [59.90959789767886]
We show that optimizing consistency training loss minimizes the Wasserstein distance between target and generated distributions.
By incorporating a discriminator into the consistency training framework, our method achieves improved FID scores on CIFAR10 and ImageNet 64$times$64 and LSUN Cat 256$times$256 datasets.
arXiv Detail & Related papers (2023-11-23T16:49:06Z) - Patch-Level Contrasting without Patch Correspondence for Accurate and
Dense Contrastive Representation Learning [79.43940012723539]
ADCLR is a self-supervised learning framework for learning accurate and dense vision representation.
Our approach achieves new state-of-the-art performance for contrastive methods.
arXiv Detail & Related papers (2023-06-23T07:38:09Z) - A Recipe for Efficient SBIR Models: Combining Relative Triplet Loss with
Batch Normalization and Knowledge Distillation [3.364554138758565]
Sketch-Based Image Retrieval (SBIR) is a crucial task in multimedia retrieval, where the goal is to retrieve a set of images that match a given sketch query.
We introduce a Relative Triplet Loss (RTL), an adapted triplet loss to overcome limitations through loss weighting based on anchors similarity.
We propose a straightforward approach to train small models efficiently with a marginal loss of accuracy through knowledge distillation.
arXiv Detail & Related papers (2023-05-30T12:41:04Z) - A New Backbone for Hyperspectral Image Reconstruction [90.48427561874402]
3D hyperspectral image (HSI) reconstruction refers to inverse process of snapshot compressive imaging.
Proposal is for a Spatial/Spectral Invariant Residual U-Net, namely SSI-ResU-Net.
We show that SSI-ResU-Net achieves competing performance with over 77.3% reduction in terms of floating-point operations.
arXiv Detail & Related papers (2021-08-17T16:20:51Z) - Effective Model Sparsification by Scheduled Grow-and-Prune Methods [73.03533268740605]
We propose a novel scheduled grow-and-prune (GaP) methodology without pre-training the dense models.
Experiments have shown that such models can match or beat the quality of highly optimized dense models at 80% sparsity on a variety of tasks.
arXiv Detail & Related papers (2021-06-18T01:03:13Z) - LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single
Image Super-Resolution and Beyond [75.37541439447314]
Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version.
This paper proposes a linearly-assembled pixel-adaptive regression network (LAPAR) to strike a sweet spot of deep model complexity and resulting SISR quality.
arXiv Detail & Related papers (2021-05-21T15:47:18Z) - HINet: Half Instance Normalization Network for Image Restoration [11.788159823037601]
We present a novel block: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration networks.
Based on HIN Block, we design a simple and powerful multi-stage network named HINet, which consists of twoworks.
With the help of HIN Block, HINet surpasses the state-of-the-art (SOTA) on various image restoration tasks.
arXiv Detail & Related papers (2021-05-13T05:25:01Z) - Enabling Retrain-free Deep Neural Network Pruning using Surrogate
Lagrangian Relaxation [2.691929135895278]
We develop a systematic weight-pruning optimization approach based on Surrogate Lagrangian relaxation ( SLR)
SLR achieves higher compression rate than state-of-the-arts under the same accuracy requirement.
Given a limited budget of retraining epochs, our approach quickly recovers the model accuracy.
arXiv Detail & Related papers (2020-12-18T07:17:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.