Pith. sign in

REVIEW 4 cited by

Simple Baselines for Image Restoration

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2204.04676 v4 pith:TH3BWRWM submitted 2022-04-10 cs.CV

Simple Baselines for Image Restoration

classification cs.CV
keywords sotaimagebaselinemethodsactivationcomputationalcostsexceeding
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original 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 pre-trained models are released at https://github.com/megvii-research/NAFNet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Splat-based 3D Scene Reconstruction with Extreme Motion-blur

    cs.CV 2026-07 conditional novelty 6.0

    An RGB-D 3D reconstruction pipeline that estimates camera poses from optical flow and depth, then uses Gaussian Splatting to refine geometry and deblur extreme motion blur without needing COLMAP initialization.

  2. MatRes: Zero-Shot Test-Time Model Adaptation for Simultaneous Matching and Restoration

    cs.CV 2026-04 unverdicted novelty 6.0

    MatRes jointly optimizes restoration and correspondence estimation at test time by enforcing conditional similarity on a single image pair and adapting lightweight modules without offline training.

  3. CANDLE: Illumination-Invariant Semantic Priors for Color Ambient Lighting Normalization

    cs.CV 2026-04 unverdicted novelty 6.0

    CANDLE uses DINOv3 semantic features as illumination-invariant priors plus custom decoder refinements to normalize images under colored ambient lighting, reporting a 1.22 dB PSNR gain and strong challenge rankings.

  4. NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results

    cs.CV 2026-04 unverdicted novelty 2.0

    The NTIRE 2026 Challenge establishes a benchmark for bitstream-corrupted video restoration and summarizes the top methods and observed trends from participating teams.