Random Noise Suppression AVO Benchmark

Deep-learning-based random-noise attenuation on pre-stack seismic shot gathers, using the clean seismic.segy AVO dataset and synthetic Gaussian / Poisson noise injection.

Task

Given a clean shot gather, the benchmark first injects synthetic random noise at a specified SNR, then trains a model to directly reconstruct the clean signal:

denoised = model(noisy_input)

This is a paired regression task with clean-target supervision. Most models directly predict the clean gather. The DDPM variant predicts diffusion noise during training and reconstructs the clean gather through reverse sampling at evaluation / inference time.

Dataset

  • Source: Clean AVO seismic.segy data
  • Current training volume: seismic.segy
  • Geometry: 201 traces per shot, time sampling interval dt = 2 ms
  • Split: Shot-level sequential 7:1:1
    • 801 training shots
    • 100 validation shots
    • 100 held-out test shots

Synthetic Noise Settings

  • Noise kinds: gaussian, poisson
  • Default sweep in training / inference scripts: SNR = -5, 0, 5 dB
  • Noise injection: per-shot variance-controlled synthetic corruption
  • Reproducibility: noise generation is seeded from experiment.seed

Model Architectures

  • UNet (unet): classic encoder-decoder with skip connections. Base channels: 32, depth: 4.
  • ResUNet (res_unet): U-Net with residual blocks. Base channels: 32, depth: 4.
  • DnCNN (dncnn): residual denoising CNN with 17 layers and 64 feature channels.
  • Attention UNet (atten_unet): U-Net with attention gates. Base channels: 32, depth: 4.
  • DDPM (ddpm): standard conditional denoising diffusion probabilistic model with reverse sampling from Gaussian noise to the clean shot gather.
  • SCRN (SCRN): Swin Transformer convolutional residual network adapted to the same random-noise benchmark pipeline.

Preprocessing

  • Amplitude correction: spherical divergence correction is skipped by default
  • Normalization: max_abs, per-shot
  • Patching: overlapping 2D patches of size 128 x 256 (trace x time)
  • Patch overlap: 50%

Training uses patched shot gathers. Inference reloads the raw volume, applies inference.shot_split, injects synthetic noise, runs patch-based reconstruction, and inverse-normalizes outputs for visualization.

Repository Structure

scripts/random_noise_suppression_avo/
|- train_denoise_unet.sh
|- train_denoise_res_unet.sh
|- train_denoise_dncnn.sh
|- train_denoise_atten_unet.sh
|- train_denoise_ddpm.sh
|- train_denoise_SCRN.sh
|- inference_denoise_unet.sh
|- inference_denoise_res_unet.sh
|- inference_denoise_dncnn.sh
|- inference_denoise_atten_unet.sh
|- inference_denoise_ddpm.sh
|- inference_denoise_SCRN.sh
`- run_all_random_noise_models.sh

configs/random_noise_suppression_avo/
|- denoise_unet.yaml
|- denoise_res_unet.yaml
|- denoise_dncnn.yaml
|- denoise_atten_unet.yaml
|- denoise_ddpm.yaml
`- denoise_SCRN.yaml

Each experiment directory is named by model, noise kind, SNR, and seed, for example:

random_noise_avo_unet_base_gaussian_snr5_seed42/
random_noise_avo_dncnn_base_poisson_snr0_seed43/
random_noise_avo_ddpm_base_gaussian_snrneg5_seed44/

Training Details

Shared benchmark defaults:

Hyperparameter Value
Loss MSE
DDPM note trains on diffusion-noise prediction and validates clean reconstruction after reverse sampling
Optimizer AdamW (lr=1e-4, weight_decay=1e-5)
Scheduler Cosine annealing (min_lr=1e-6)
Epochs 200
Gradient clipping 1.0
Seeds 42, 43, 44 by default in shell sweeps
Batch size 192 in current YAML defaults

Usage

Train One Model Family

bash scripts/random_noise_suppression_avo/train_denoise_unet.sh

or

bash scripts/random_noise_suppression_avo/train_denoise_ddpm.sh

Each training shell script sweeps:

  • noise kind
  • SNR
  • seed

by rewriting a temporary YAML config before calling torchrun.

Run Inference

bash scripts/random_noise_suppression_avo/inference_denoise_unet.sh

Inference outputs:

  • per-shot metrics CSV
  • summary JSON
  • visualizations
  • optional .npy files
  • multi-seed mean/std aggregation JSON

Run All Model Families

bash scripts/random_noise_suppression_avo/run_all_random_noise_models.sh

Current total-run script executes:

  1. unet
  2. dncnn
  3. res_unet
  4. atten_unet
  5. ddpm

Each model is trained first, then its inference sweep is launched immediately after training finishes.

Inference Outputs

For each experiment, the inference directory typically contains:

inference/
|- inference.log
|- metrics_per_shot.csv
|- metrics_summary.json
|- visualizations/
`- npy/                    # only when save_npy=true

Metrics

The benchmark reports:

  • snr
  • psnr
  • ssim
  • mae
  • mse
  • rmse

for three groups:

  • noisy: noisy input vs clean target
  • denoised: model prediction vs clean target
  • delta: denoised - noisy

Metrics are computed in the normalized domain. Saved visualization outputs are inverse-normalized back to the original amplitude domain.

Notes

  • This benchmark injects synthetic random noise once per experiment before patch extraction; it is not an epoch-wise dynamic noise augmentation setup.
  • Shot-level inference uses the held-out test shot defined by inference.shot_split.
  • Batch size and patch size may need adjustment for memory-heavy models such as DnCNN and DDPM.

References

  • Ronneberger et al., U-Net: Convolutional Networks for Biomedical Image Segmentation, MICCAI 2015
  • He et al., Deep Residual Learning for Image Recognition, CVPR 2016
  • Zhang et al., Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising, IEEE TIP 2017
  • Ho et al., Denoising Diffusion Probabilistic Models, NeurIPS 2020
  • Song et al., Denoising Diffusion Implicit Models, ICLR 2021
  • Oktay et al., Attention U-Net: Learning Where to Look for the Pancreas, MIDL 2018
  • Gao et al., Swin Transformer for simultaneous denoising and interpolation of seismic data, Computers and Geosciences 2024
  • SEG C3 Velocity Model: https://wiki.seg.org/wiki/C3

Results

Mean +- std over available seeds, computed from *_seed_stats/metrics_summary_mean_std.json. Metrics are reported in the normalized domain. Raw (noisy) is the synthetic noisy input before denoising.

Gaussian Noise

SNR -5 dB

Method Parameters (M) SNR PSNR SSIM MAE MSE RMSE EB_WSE_MEDIUM_40_70_NE EB_WSE_MEDIUM_40_70_SNR EB_WSE_STRONG_70_100_NE EB_WSE_STRONG_70_100_SNR EB_WSE_VERY_WEAK_5_20_NE EB_WSE_VERY_WEAK_5_20_SNR EB_WSE_WEAK_20_40_NE EB_WSE_WEAK_20_40_SNR FB_FRE_HIGH_ENERGY_RATIO FB_FRE_HIGH_FREQUENCY_RANGE_HZ FB_FRE_HIGH_NE FB_FRE_HIGH_SNR FB_FRE_LOW_ENERGY_RATIO FB_FRE_LOW_FREQUENCY_RANGE_HZ FB_FRE_LOW_NE FB_FRE_LOW_SNR FB_FRE_MID_ENERGY_RATIO FB_FRE_MID_FREQUENCY_RANGE_HZ FB_FRE_MID_NE FB_FRE_MID_SNR FB_FRE_VERY_HIGH_ENERGY_RATIO FB_FRE_VERY_HIGH_FREQUENCY_RANGE_HZ FB_FRE_VERY_HIGH_NE FB_FRE_VERY_HIGH_SNR
Raw (noisy) - -5.0000+-0.0015 28.4184+-0.0015 0.6663+-0.0002 0.030315+-0.000008 0.001448+-0.000001 0.037994+-0.000007 30.056404+-0.003195 -29.5408+-0.0009 0.974550+-0.000441 0.2240+-0.0039 217.468024+-0.075775 -46.7401+-0.0030 100.131537+-0.019746 -39.9965+-0.0018 0.168114+-0.000000 48.3333-73.5333 1.841567+-0.000122 -5.2710+-0.0006 0.283209+-0.000000 6.3333-23.1333 1.150310+-0.000255 -1.2055+-0.0019 0.425271+-0.000000 23.1333-48.3333 1.147630+-0.000330 -1.1892+-0.0025 0.001317+-0.000000 73.5333-90.3333 18.962028+-0.014011 -25.2465+-0.0056
UNet 7.76 8.9440+-0.0034 42.3624+-0.0034 0.9807+-0.0000 0.004273+-0.000002 0.000058+-0.000000 0.007623+-0.000003 2.416080+-0.000817 -7.6466+-0.0029 0.338792+-0.000149 9.4048+-0.0037 15.867472+-0.007823 -23.9986+-0.0043 7.376587+-0.006652 -17.3406+-0.0071 0.168114+-0.000000 48.3333-73.5333 0.371155+-0.000550 8.6215+-0.0129 0.283209+-0.000000 6.3333-23.1333 0.350323+-0.000279 9.1190+-0.0065 0.425271+-0.000000 23.1333-48.3333 0.308464+-0.000132 10.2247+-0.0039 0.001317+-0.000000 73.5333-90.3333 1.857709+-0.001298 -5.2139+-0.0053
DnCNN 0.56 8.9707+-0.0035 42.3891+-0.0035 0.9810+-0.0000 0.004693+-0.000001 0.000058+-0.000000 0.007602+-0.000003 3.098011+-0.001746 -9.8080+-0.0049 0.324189+-0.000137 9.7859+-0.0037 20.750542+-0.000822 -26.3332+-0.0001 9.744805+-0.001931 -19.7626+-0.0019 0.168114+-0.000000 48.3333-73.5333 0.367070+-0.000116 8.7256+-0.0027 0.283209+-0.000000 6.3333-23.1333 0.336299+-0.000336 9.4715+-0.0087 0.425271+-0.000000 23.1333-48.3333 0.297151+-0.000085 10.5476+-0.0027 0.001317+-0.000000 73.5333-90.3333 2.415984+-0.004356 -7.4367+-0.0128
ResUNet 8.11 8.0137+-0.0010 41.4321+-0.0010 0.9801+-0.0000 0.005013+-0.000001 0.000072+-0.000000 0.008487+-0.000001 3.284017+-0.000458 -10.3149+-0.0014 0.364963+-0.000046 8.7602+-0.0010 22.633412+-0.010049 -27.0879+-0.0039 10.442392+-0.004309 -20.3616+-0.0033 0.168114+-0.000000 48.3333-73.5333 0.442797+-0.000388 7.1028+-0.0073 0.283209+-0.000000 6.3333-23.1333 0.335051+-0.000210 9.5125+-0.0057 0.425271+-0.000000 23.1333-48.3333 0.324708+-0.000281 9.7780+-0.0074 0.001317+-0.000000 73.5333-90.3333 2.940459+-0.002013 -9.1227+-0.0075
Attention UNet 7.85 9.2655+-0.0043 42.6839+-0.0043 0.9841+-0.0000 0.003342+-0.000001 0.000054+-0.000000 0.007349+-0.000003 1.420080+-0.001250 -3.0417+-0.0072 0.338450+-0.000173 9.4140+-0.0045 10.383467+-0.018701 -20.2944+-0.0172 3.086211+-0.005139 -9.7630+-0.0130 0.168114+-0.000000 48.3333-73.5333 0.379595+-0.000461 8.4401+-0.0106 0.283209+-0.000000 6.3333-23.1333 0.316613+-0.000383 9.9980+-0.0105 0.425271+-0.000000 23.1333-48.3333 0.300578+-0.000210 10.4476+-0.0062 0.001317+-0.000000 73.5333-90.3333 1.982228+-0.000575 -5.7680+-0.0028
DDPM 33.30 7.1648+-0.1578 40.5832+-0.1578 0.9638+-0.0010 0.006926+-0.000121 0.000089+-0.000004 0.009404+-0.000181 6.014312+-0.110613 -15.4517+-0.1591 0.308027+-0.003648 10.2626+-0.0994 47.100793+-1.606397 -33.1509+-0.2805 21.533452+-0.800196 -26.4012+-0.2870 0.168114+-0.000000 48.3333-73.5333 0.460230+-0.009898 6.8349+-0.1815 0.283209+-0.000000 6.3333-23.1333 0.327191+-0.004703 9.7471+-0.1208 0.425271+-0.000000 23.1333-48.3333 0.334689+-0.005003 9.5485+-0.1310 0.001317+-0.000000 73.5333-90.3333 3.874504+-0.119669 -11.4459+-0.2489

SNR 0 dB

Method Parameters (M) SNR PSNR SSIM MAE MSE RMSE EB_WSE_MEDIUM_40_70_NE EB_WSE_MEDIUM_40_70_SNR EB_WSE_STRONG_70_100_NE EB_WSE_STRONG_70_100_SNR EB_WSE_VERY_WEAK_5_20_NE EB_WSE_VERY_WEAK_5_20_SNR EB_WSE_WEAK_20_40_NE EB_WSE_WEAK_20_40_SNR FB_FRE_HIGH_ENERGY_RATIO FB_FRE_HIGH_FREQUENCY_RANGE_HZ FB_FRE_HIGH_NE FB_FRE_HIGH_SNR FB_FRE_LOW_ENERGY_RATIO FB_FRE_LOW_FREQUENCY_RANGE_HZ FB_FRE_LOW_NE FB_FRE_LOW_SNR FB_FRE_MID_ENERGY_RATIO FB_FRE_MID_FREQUENCY_RANGE_HZ FB_FRE_MID_NE FB_FRE_MID_SNR FB_FRE_VERY_HIGH_ENERGY_RATIO FB_FRE_VERY_HIGH_FREQUENCY_RANGE_HZ FB_FRE_VERY_HIGH_NE FB_FRE_VERY_HIGH_SNR
Raw (noisy) - 0.0000+-0.0015 33.4184+-0.0015 0.8644+-0.0001 0.017047+-0.000004 0.000458+-0.000000 0.021365+-0.000004 16.901958+-0.001796 -24.5408+-0.0009 0.548030+-0.000248 5.2240+-0.0039 122.291257+-0.042611 -41.7401+-0.0030 56.308101+-0.011104 -34.9965+-0.0018 0.168114+-0.000000 48.3333-73.5333 1.035589+-0.000068 -0.2710+-0.0006 0.283209+-0.000000 6.3333-23.1333 0.646867+-0.000144 3.7945+-0.0019 0.425271+-0.000000 23.1333-48.3333 0.645360+-0.000186 3.8108+-0.0025 0.001317+-0.000000 73.5333-90.3333 10.663132+-0.007879 -20.2465+-0.0056
UNet 7.76 10.5129+-0.0048 43.9313+-0.0048 0.9847+-0.0000 0.003534+-0.000002 0.000040+-0.000000 0.006361+-0.000003 1.862257+-0.001138 -5.3904+-0.0051 0.285767+-0.000168 10.8867+-0.0049 11.745703+-0.009011 -21.3908+-0.0068 5.497729+-0.002016 -14.7914+-0.0029 0.168114+-0.000000 48.3333-73.5333 0.295392+-0.000340 10.6085+-0.0097 0.283209+-0.000000 6.3333-23.1333 0.298379+-0.000381 10.5175+-0.0108 0.425271+-0.000000 23.1333-48.3333 0.250014+-0.000159 12.0534+-0.0055 0.001317+-0.000000 73.5333-90.3333 1.658566+-0.001730 -4.2297+-0.0092
DnCNN 0.56 11.9518+-0.0034 45.3702+-0.0034 0.9897+-0.0000 0.003337+-0.000001 0.000029+-0.000000 0.005394+-0.000002 2.139022+-0.000466 -6.5928+-0.0021 0.232244+-0.000112 12.6831+-0.0042 13.817607+-0.005660 -22.8012+-0.0034 6.403740+-0.003271 -16.1159+-0.0043 0.168114+-0.000000 48.3333-73.5333 0.269423+-0.000325 11.4154+-0.0105 0.283209+-0.000000 6.3333-23.1333 0.230354+-0.000210 12.7601+-0.0076 0.425271+-0.000000 23.1333-48.3333 0.211891+-0.000061 13.4842+-0.0028 0.001317+-0.000000 73.5333-90.3333 1.749333+-0.002662 -4.6522+-0.0117
ResUNet 8.11 9.7121+-0.0008 43.1305+-0.0008 0.9868+-0.0000 0.004095+-0.000000 0.000049+-0.000000 0.006980+-0.000000 2.710213+-0.000282 -8.6483+-0.0009 0.300704+-0.000028 10.4445+-0.0009 18.291564+-0.005380 -25.2383+-0.0025 8.421791+-0.001544 -18.4938+-0.0015 0.168114+-0.000000 48.3333-73.5333 0.361138+-0.000298 8.8818+-0.0068 0.283209+-0.000000 6.3333-23.1333 0.258261+-0.000021 11.7699+-0.0011 0.425271+-0.000000 23.1333-48.3333 0.258926+-0.000258 11.7461+-0.0084 0.001317+-0.000000 73.5333-90.3333 2.724224+-0.001661 -8.4668+-0.0051
Attention UNet 7.85 11.1362+-0.0024 44.5546+-0.0024 0.9894+-0.0000 0.002881+-0.000000 0.000035+-0.000000 0.005924+-0.000002 1.388531+-0.001529 -2.8484+-0.0096 0.271811+-0.000078 11.3208+-0.0025 6.901314+-0.012339 -16.7698+-0.0152 3.179268+-0.003148 -10.0299+-0.0084 0.168114+-0.000000 48.3333-73.5333 0.313669+-0.000186 10.1016+-0.0052 0.283209+-0.000000 6.3333-23.1333 0.239186+-0.000133 12.4375+-0.0046 0.425271+-0.000000 23.1333-48.3333 0.231816+-0.000084 12.7057+-0.0035 0.001317+-0.000000 73.5333-90.3333 2.011722+-0.002298 -5.8902+-0.0083
DDPM 33.30 7.3520+-0.1258 40.7704+-0.1258 0.9704+-0.0008 0.006917+-0.000085 0.000087+-0.000003 0.009235+-0.000140 6.400374+-0.083429 -15.9559+-0.1142 0.267865+-0.003680 11.5158+-0.1174 51.545130+-1.185846 -33.8794+-0.2025 23.047020+-0.829319 -26.9387+-0.2956 0.168114+-0.000000 48.3333-73.5333 0.458381+-0.006855 6.9020+-0.1255 0.283209+-0.000000 6.3333-23.1333 0.299931+-0.003971 10.5350+-0.1139 0.425271+-0.000000 23.1333-48.3333 0.312099+-0.003603 10.1834+-0.1035 0.001317+-0.000000 73.5333-90.3333 4.238241+-0.076306 -12.2105+-0.1462

SNR 5 dB

Method Parameters (M) SNR PSNR SSIM MAE MSE RMSE EB_WSE_MEDIUM_40_70_NE EB_WSE_MEDIUM_40_70_SNR EB_WSE_STRONG_70_100_NE EB_WSE_STRONG_70_100_SNR EB_WSE_VERY_WEAK_5_20_NE EB_WSE_VERY_WEAK_5_20_SNR EB_WSE_WEAK_20_40_NE EB_WSE_WEAK_20_40_SNR FB_FRE_HIGH_ENERGY_RATIO FB_FRE_HIGH_FREQUENCY_RANGE_HZ FB_FRE_HIGH_NE FB_FRE_HIGH_SNR FB_FRE_LOW_ENERGY_RATIO FB_FRE_LOW_FREQUENCY_RANGE_HZ FB_FRE_LOW_NE FB_FRE_LOW_SNR FB_FRE_MID_ENERGY_RATIO FB_FRE_MID_FREQUENCY_RANGE_HZ FB_FRE_MID_NE FB_FRE_MID_SNR FB_FRE_VERY_HIGH_ENERGY_RATIO FB_FRE_VERY_HIGH_FREQUENCY_RANGE_HZ FB_FRE_VERY_HIGH_NE FB_FRE_VERY_HIGH_SNR
Raw (noisy) - 5.0000+-0.0015 38.4184+-0.0015 0.9528+-0.0000 0.009587+-0.000002 0.000145+-0.000000 0.012015+-0.000002 9.504669+-0.001010 -19.5408+-0.0009 0.308180+-0.000139 10.2240+-0.0039 68.769427+-0.023962 -36.7401+-0.0030 31.664372+-0.006244 -29.9965+-0.0018 0.168114+-0.000000 48.3333-73.5333 0.582355+-0.000039 4.7290+-0.0006 0.283209+-0.000000 6.3333-23.1333 0.363760+-0.000081 8.7945+-0.0019 0.425271+-0.000000 23.1333-48.3333 0.362912+-0.000104 8.8108+-0.0025 0.001317+-0.000000 73.5333-90.3333 5.996320+-0.004431 -15.2465+-0.0056
UNet 7.76 12.7151+-0.0046 46.1335+-0.0046 0.9911+-0.0000 0.002776+-0.000001 0.000024+-0.000000 0.004937+-0.000003 1.481680+-0.000344 -3.4066+-0.0018 0.221581+-0.000125 13.0955+-0.0048 9.064477+-0.003318 -19.1393+-0.0034 4.239337+-0.001748 -12.5320+-0.0035 0.168114+-0.000000 48.3333-73.5333 0.239064+-0.000116 12.4555+-0.0039 0.283209+-0.000000 6.3333-23.1333 0.215258+-0.000339 13.3532+-0.0133 0.425271+-0.000000 23.1333-48.3333 0.191701+-0.000072 14.3603+-0.0033 0.001317+-0.000000 73.5333-90.3333 1.533126+-0.002486 -3.5443+-0.0129
DnCNN 0.56 15.1037+-0.0044 48.5221+-0.0044 0.9949+-0.0000 0.002262+-0.000001 0.000014+-0.000000 0.003753+-0.000002 1.446875+-0.000322 -3.1992+-0.0019 0.163963+-0.000095 15.7072+-0.0050 8.230538+-0.004905 -18.2988+-0.0053 3.831710+-0.001966 -11.6548+-0.0046 0.168114+-0.000000 48.3333-73.5333 0.188635+-0.000053 14.5166+-0.0021 0.283209+-0.000000 6.3333-23.1333 0.153169+-0.000161 16.3053+-0.0090 0.425271+-0.000000 23.1333-48.3333 0.145783+-0.000055 16.7324+-0.0035 0.001317+-0.000000 73.5333-90.3333 1.304467+-0.001570 -2.1151+-0.0091
ResUNet 8.11 10.8324+-0.0010 44.2508+-0.0010 0.9910+-0.0000 0.003324+-0.000000 0.000038+-0.000000 0.006137+-0.000001 2.112371+-0.000957 -6.4850+-0.0041 0.270219+-0.000031 11.3781+-0.0010 13.936359+-0.003499 -22.8763+-0.0022 6.320756+-0.001966 -16.0011+-0.0029 0.168114+-0.000000 48.3333-73.5333 0.310006+-0.000186 10.2124+-0.0054 0.283209+-0.000000 6.3333-23.1333 0.214654+-0.000097 13.3832+-0.0039 0.425271+-0.000000 23.1333-48.3333 0.218305+-0.000050 13.2314+-0.0019 0.001317+-0.000000 73.5333-90.3333 2.720500+-0.002350 -8.4605+-0.0080
Attention UNet 7.85 12.3464+-0.0054 45.7647+-0.0053 0.9926+-0.0000 0.002436+-0.000001 0.000027+-0.000000 0.005154+-0.000003 1.302140+-0.000202 -2.2909+-0.0012 0.235823+-0.000151 12.5582+-0.0056 6.489683+-0.001444 -16.2294+-0.0022 2.849174+-0.001911 -9.0745+-0.0057 0.168114+-0.000000 48.3333-73.5333 0.273493+-0.000307 11.3198+-0.0095 0.283209+-0.000000 6.3333-23.1333 0.198473+-0.000110 14.0576+-0.0047 0.425271+-0.000000 23.1333-48.3333 0.194307+-0.000077 14.2399+-0.0036 0.001317+-0.000000 73.5333-90.3333 1.905562+-0.001105 -5.4070+-0.0026
DDPM 33.30 7.6850+-0.1814 41.1034+-0.1814 0.9725+-0.0011 0.006681+-0.000118 0.000081+-0.000004 0.008914+-0.000193 6.443338+-0.098793 -15.9941+-0.1425 0.238385+-0.004719 12.5798+-0.1693 51.770507+-1.471348 -33.8796+-0.2459 23.298755+-0.920540 -26.9985+-0.3178 0.168114+-0.000000 48.3333-73.5333 0.439799+-0.009433 7.2924+-0.1815 0.283209+-0.000000 6.3333-23.1333 0.279271+-0.005615 11.1908+-0.1729 0.425271+-0.000000 23.1333-48.3333 0.287681+-0.005280 10.9234+-0.1639 0.001317+-0.000000 73.5333-90.3333 4.253336+-0.100793 -12.2218+-0.1919

Poisson Noise

SNR -5 dB

Method Parameters (M) SNR PSNR SSIM MAE MSE RMSE EB_WSE_MEDIUM_40_70_NE EB_WSE_MEDIUM_40_70_SNR EB_WSE_STRONG_70_100_NE EB_WSE_STRONG_70_100_SNR EB_WSE_VERY_WEAK_5_20_NE EB_WSE_VERY_WEAK_5_20_SNR EB_WSE_WEAK_20_40_NE EB_WSE_WEAK_20_40_SNR FB_FRE_HIGH_ENERGY_RATIO FB_FRE_HIGH_FREQUENCY_RANGE_HZ FB_FRE_HIGH_NE FB_FRE_HIGH_SNR FB_FRE_LOW_ENERGY_RATIO FB_FRE_LOW_FREQUENCY_RANGE_HZ FB_FRE_LOW_NE FB_FRE_LOW_SNR FB_FRE_MID_ENERGY_RATIO FB_FRE_MID_FREQUENCY_RANGE_HZ FB_FRE_MID_NE FB_FRE_MID_SNR FB_FRE_VERY_HIGH_ENERGY_RATIO FB_FRE_VERY_HIGH_FREQUENCY_RANGE_HZ FB_FRE_VERY_HIGH_NE FB_FRE_VERY_HIGH_SNR
Raw (noisy) - -4.9986+-0.0015 28.4198+-0.0015 0.6663+-0.0001 0.030308+-0.000004 0.001447+-0.000000 0.037988+-0.000007 30.055742+-0.008101 -29.5406+-0.0024 0.974447+-0.000121 0.2249+-0.0011 217.357200+-0.102979 -46.7357+-0.0040 100.096922+-0.017429 -39.9936+-0.0012 0.168114+-0.000000 48.3333-73.5333 1.841246+-0.000500 -5.2697+-0.0024 0.283209+-0.000000 6.3333-23.1333 1.149769+-0.000100 -1.2014+-0.0009 0.425271+-0.000000 23.1333-48.3333 1.147469+-0.000565 -1.1882+-0.0043 0.001317+-0.000000 73.5333-90.3333 18.965560+-0.004406 -25.2484+-0.0018
UNet 7.76 8.9857+-0.0031 42.4041+-0.0031 0.9808+-0.0000 0.004256+-0.000000 0.000058+-0.000000 0.007587+-0.000003 2.415076+-0.002099 -7.6446+-0.0074 0.337022+-0.000162 9.4499+-0.0042 15.838296+-0.020752 -23.9837+-0.0112 7.364007+-0.012769 -17.3268+-0.0150 0.168114+-0.000000 48.3333-73.5333 0.369695+-0.000207 8.6562+-0.0048 0.283209+-0.000000 6.3333-23.1333 0.346966+-0.000291 9.2024+-0.0073 0.425271+-0.000000 23.1333-48.3333 0.307719+-0.000289 10.2453+-0.0085 0.001317+-0.000000 73.5333-90.3333 1.854940+-0.000681 -5.2019+-0.0030
DnCNN 0.56 9.1529+-0.0032 42.5713+-0.0032 0.9817+-0.0000 0.004577+-0.000001 0.000056+-0.000000 0.007444+-0.000003 2.963686+-0.002757 -9.4231+-0.0081 0.318671+-0.000195 9.9353+-0.0053 20.184007+-0.006813 -26.0929+-0.0025 9.310510+-0.014889 -19.3658+-0.0138 0.168114+-0.000000 48.3333-73.5333 0.362543+-0.000170 8.8329+-0.0045 0.283209+-0.000000 6.3333-23.1333 0.327873+-0.000558 9.6921+-0.0147 0.425271+-0.000000 23.1333-48.3333 0.294731+-0.000087 10.6183+-0.0027 0.001317+-0.000000 73.5333-90.3333 2.304461+-0.000964 -7.0340+-0.0028
ResUNet 8.11 8.0629+-0.0008 41.4812+-0.0008 0.9801+-0.0000 0.005003+-0.000001 0.000071+-0.000000 0.008439+-0.000001 3.283250+-0.001270 -10.3128+-0.0034 0.362541+-0.000058 8.8179+-0.0015 22.618869+-0.015280 -27.0822+-0.0056 10.436372+-0.009197 -20.3564+-0.0077 0.168114+-0.000000 48.3333-73.5333 0.439369+-0.000187 7.1704+-0.0042 0.283209+-0.000000 6.3333-23.1333 0.333929+-0.000445 9.5405+-0.0117 0.425271+-0.000000 23.1333-48.3333 0.322530+-0.000288 9.8364+-0.0081 0.001317+-0.000000 73.5333-90.3333 2.927225+-0.003374 -9.0763+-0.0105
Attention UNet 7.85 9.2677+-0.0050 42.6861+-0.0050 0.9841+-0.0000 0.003340+-0.000001 0.000054+-0.000000 0.007347+-0.000004 1.457137+-0.003146 -3.2655+-0.0188 0.338279+-0.000204 9.4182+-0.0053 10.006613+-0.029775 -19.9800+-0.0254 3.113864+-0.005793 -9.8431+-0.0157 0.168114+-0.000000 48.3333-73.5333 0.381022+-0.000305 8.4090+-0.0067 0.283209+-0.000000 6.3333-23.1333 0.316770+-0.000630 9.9933+-0.0171 0.425271+-0.000000 23.1333-48.3333 0.299608+-0.000175 10.4757+-0.0051 0.001317+-0.000000 73.5333-90.3333 2.009310+-0.003554 -5.8739+-0.0114
DDPM 33.30 6.8701+-0.2412 40.2885+-0.2412 0.9656+-0.0015 0.007193+-0.000200 0.000096+-0.000005 0.009725+-0.000274 6.228295+-0.163362 -15.7623+-0.2347 0.316087+-0.005547 10.0376+-0.1516 49.867653+-2.345451 -33.6700+-0.4037 22.349018+-1.024055 -26.7452+-0.3855 0.168114+-0.000000 48.3333-73.5333 0.480265+-0.016030 6.4594+-0.2890 0.283209+-0.000000 6.3333-23.1333 0.341868+-0.010202 9.3654+-0.2595 0.425271+-0.000000 23.1333-48.3333 0.348159+-0.009248 9.2047+-0.2314 0.001317+-0.000000 73.5333-90.3333 4.089157+-0.171922 -11.9225+-0.3729

SNR 0 dB

Method Parameters (M) SNR PSNR SSIM MAE MSE RMSE EB_WSE_MEDIUM_40_70_NE EB_WSE_MEDIUM_40_70_SNR EB_WSE_STRONG_70_100_NE EB_WSE_STRONG_70_100_SNR EB_WSE_VERY_WEAK_5_20_NE EB_WSE_VERY_WEAK_5_20_SNR EB_WSE_WEAK_20_40_NE EB_WSE_WEAK_20_40_SNR FB_FRE_HIGH_ENERGY_RATIO FB_FRE_HIGH_FREQUENCY_RANGE_HZ FB_FRE_HIGH_NE FB_FRE_HIGH_SNR FB_FRE_LOW_ENERGY_RATIO FB_FRE_LOW_FREQUENCY_RANGE_HZ FB_FRE_LOW_NE FB_FRE_LOW_SNR FB_FRE_MID_ENERGY_RATIO FB_FRE_MID_FREQUENCY_RANGE_HZ FB_FRE_MID_NE FB_FRE_MID_SNR FB_FRE_VERY_HIGH_ENERGY_RATIO FB_FRE_VERY_HIGH_FREQUENCY_RANGE_HZ FB_FRE_VERY_HIGH_NE FB_FRE_VERY_HIGH_SNR
Raw (noisy) - 0.0023+-0.0012 33.4206+-0.0012 0.8645+-0.0000 0.017041+-0.000002 0.000458+-0.000000 0.021360+-0.000003 16.897970+-0.004420 -24.5386+-0.0022 0.548122+-0.000078 5.2225+-0.0012 122.192401+-0.050008 -41.7331+-0.0035 56.272479+-0.003774 -34.9910+-0.0005 0.168114+-0.000000 48.3333-73.5333 1.035247+-0.000049 -0.2683+-0.0004 0.283209+-0.000000 6.3333-23.1333 0.646679+-0.000100 3.7971+-0.0014 0.425271+-0.000000 23.1333-48.3333 0.645245+-0.000461 3.8120+-0.0062 0.001317+-0.000000 73.5333-90.3333 10.666173+-0.001591 -20.2493+-0.0019
UNet 7.76 10.2685+-0.0045 43.6869+-0.0045 0.9836+-0.0000 0.003591+-0.000001 0.000043+-0.000000 0.006543+-0.000003 1.889969+-0.000705 -5.5192+-0.0033 0.294167+-0.000159 10.6331+-0.0049 11.981634+-0.005965 -21.5637+-0.0042 5.589865+-0.005678 -14.9357+-0.0088 0.168114+-0.000000 48.3333-73.5333 0.302042+-0.000172 10.4159+-0.0051 0.283209+-0.000000 6.3333-23.1333 0.306526+-0.000292 10.2817+-0.0086 0.425271+-0.000000 23.1333-48.3333 0.251918+-0.000122 11.9870+-0.0046 0.001317+-0.000000 73.5333-90.3333 1.700620+-0.001753 -4.4417+-0.0097
DnCNN 0.56 11.9815+-0.0031 45.3999+-0.0031 0.9897+-0.0000 0.003295+-0.000001 0.000029+-0.000000 0.005376+-0.000002 2.079791+-0.000670 -6.3499+-0.0029 0.232617+-0.000107 12.6689+-0.0040 13.344696+-0.009765 -22.4992+-0.0063 6.179797+-0.002493 -15.8068+-0.0033 0.168114+-0.000000 48.3333-73.5333 0.266328+-0.000111 11.5152+-0.0037 0.283209+-0.000000 6.3333-23.1333 0.230965+-0.000154 12.7369+-0.0059 0.425271+-0.000000 23.1333-48.3333 0.211589+-0.000091 13.4965+-0.0039 0.001317+-0.000000 73.5333-90.3333 1.752735+-0.000788 -4.6601+-0.0031
ResUNet 8.11 9.6522+-0.0017 43.0706+-0.0017 0.9866+-0.0000 0.004132+-0.000001 0.000049+-0.000000 0.007028+-0.000002 2.740937+-0.000949 -8.7459+-0.0027 0.302456+-0.000073 10.3936+-0.0022 18.531887+-0.013041 -25.3514+-0.0060 8.541418+-0.001232 -18.6162+-0.0013 0.168114+-0.000000 48.3333-73.5333 0.362209+-0.000080 8.8562+-0.0018 0.283209+-0.000000 6.3333-23.1333 0.261251+-0.000237 11.6697+-0.0082 0.425271+-0.000000 23.1333-48.3333 0.259974+-0.000213 11.7098+-0.0073 0.001317+-0.000000 73.5333-90.3333 2.777232+-0.001871 -8.6346+-0.0041
Attention UNet 7.85 11.1553+-0.0062 44.5737+-0.0062 0.9893+-0.0000 0.002898+-0.000001 0.000035+-0.000000 0.005911+-0.000004 1.390313+-0.000376 -2.8592+-0.0024 0.271191+-0.000200 11.3407+-0.0065 6.832799+-0.013773 -16.6845+-0.0180 3.183770+-0.002159 -10.0437+-0.0061 0.168114+-0.000000 48.3333-73.5333 0.311212+-0.000090 10.1706+-0.0021 0.283209+-0.000000 6.3333-23.1333 0.241095+-0.000265 12.3663+-0.0099 0.425271+-0.000000 23.1333-48.3333 0.232303+-0.000295 12.6878+-0.0110 0.001317+-0.000000 73.5333-90.3333 1.948963+-0.002379 -5.6070+-0.0092
DDPM 33.30 7.0527+-0.6239 40.4711+-0.6239 0.9676+-0.0048 0.007126+-0.000446 0.000095+-0.000016 0.009612+-0.000744 6.653783+-0.446833 -16.2410+-0.5495 0.276525+-0.017426 11.2760+-0.5134 53.515679+-4.622386 -34.1060+-0.6560 24.062672+-2.095657 -27.2173+-0.6063 0.168114+-0.000000 48.3333-73.5333 0.475384+-0.035410 6.6314+-0.6020 0.283209+-0.000000 6.3333-23.1333 0.312405+-0.023336 10.2214+-0.6120 0.425271+-0.000000 23.1333-48.3333 0.322814+-0.021756 9.9253+-0.5612 0.001317+-0.000000 73.5333-90.3333 4.417432+-0.370473 -12.5098+-0.6560

SNR 5 dB

Method Parameters (M) SNR PSNR SSIM MAE MSE RMSE EB_WSE_MEDIUM_40_70_NE EB_WSE_MEDIUM_40_70_SNR EB_WSE_STRONG_70_100_NE EB_WSE_STRONG_70_100_SNR EB_WSE_VERY_WEAK_5_20_NE EB_WSE_VERY_WEAK_5_20_SNR EB_WSE_WEAK_20_40_NE EB_WSE_WEAK_20_40_SNR FB_FRE_HIGH_ENERGY_RATIO FB_FRE_HIGH_FREQUENCY_RANGE_HZ FB_FRE_HIGH_NE FB_FRE_HIGH_SNR FB_FRE_LOW_ENERGY_RATIO FB_FRE_LOW_FREQUENCY_RANGE_HZ FB_FRE_LOW_NE FB_FRE_LOW_SNR FB_FRE_MID_ENERGY_RATIO FB_FRE_MID_FREQUENCY_RANGE_HZ FB_FRE_MID_NE FB_FRE_MID_SNR FB_FRE_VERY_HIGH_ENERGY_RATIO FB_FRE_VERY_HIGH_FREQUENCY_RANGE_HZ FB_FRE_VERY_HIGH_NE FB_FRE_VERY_HIGH_SNR
Raw (noisy) - 5.0013+-0.0005 38.4197+-0.0005 0.9528+-0.0000 0.009585+-0.000001 0.000145+-0.000000 0.012013+-0.000001 9.502945+-0.000967 -19.5391+-0.0007 0.308110+-0.000111 10.2259+-0.0031 68.744539+-0.029754 -36.7371+-0.0038 31.665301+-0.014444 -29.9967+-0.0040 0.168114+-0.000000 48.3333-73.5333 0.582273+-0.000219 4.7300+-0.0031 0.283209+-0.000000 6.3333-23.1333 0.363669+-0.000022 8.7967+-0.0007 0.425271+-0.000000 23.1333-48.3333 0.362916+-0.000190 8.8104+-0.0045 0.001317+-0.000000 73.5333-90.3333 5.996074+-0.000881 -15.2461+-0.0005
UNet 7.76 12.6735+-0.0009 46.0919+-0.0009 0.9909+-0.0000 0.002779+-0.000000 0.000025+-0.000000 0.004961+-0.000001 1.481825+-0.000701 -3.4074+-0.0040 0.222778+-0.000029 13.0481+-0.0011 9.008784+-0.003577 -19.0862+-0.0034 4.219501+-0.002957 -12.4921+-0.0066 0.168114+-0.000000 48.3333-73.5333 0.239523+-0.000217 12.4398+-0.0074 0.283209+-0.000000 6.3333-23.1333 0.216420+-0.000178 13.3066+-0.0068 0.425271+-0.000000 23.1333-48.3333 0.191949+-0.000036 14.3481+-0.0016 0.001317+-0.000000 73.5333-90.3333 1.547839+-0.002906 -3.6236+-0.0174
DnCNN 0.56 14.9594+-0.0020 48.3778+-0.0020 0.9947+-0.0000 0.002342+-0.000000 0.000015+-0.000000 0.003815+-0.000001 1.522983+-0.000381 -3.6445+-0.0022 0.165433+-0.000050 15.6299+-0.0027 8.890889+-0.004972 -18.9705+-0.0049 4.179185+-0.003171 -12.4093+-0.0066 0.168114+-0.000000 48.3333-73.5333 0.191927+-0.000064 14.3658+-0.0032 0.283209+-0.000000 6.3333-23.1333 0.156217+-0.000152 16.1340+-0.0084 0.425271+-0.000000 23.1333-48.3333 0.147813+-0.000084 16.6122+-0.0049 0.001317+-0.000000 73.5333-90.3333 1.332505+-0.001006 -2.3057+-0.0060
ResUNet 8.11 10.8216+-0.0028 44.2400+-0.0028 0.9910+-0.0000 0.003328+-0.000001 0.000038+-0.000000 0.006145+-0.000002 2.117962+-0.000157 -6.5076+-0.0007 0.270441+-0.000104 11.3697+-0.0032 13.996343+-0.003306 -22.9134+-0.0018 6.346291+-0.000121 -16.0362+-0.0005 0.168114+-0.000000 48.3333-73.5333 0.312489+-0.000390 10.1357+-0.0105 0.283209+-0.000000 6.3333-23.1333 0.213235+-0.000057 13.4415+-0.0022 0.425271+-0.000000 23.1333-48.3333 0.217869+-0.000157 13.2491+-0.0063 0.001317+-0.000000 73.5333-90.3333 2.743843+-0.000951 -8.5181+-0.0040
Attention UNet 7.85 12.6766+-0.0026 46.0950+-0.0026 0.9927+-0.0000 0.002410+-0.000000 0.000025+-0.000000 0.004963+-0.000002 1.269969+-0.000532 -2.0736+-0.0038 0.226817+-0.000076 12.8987+-0.0029 6.554225+-0.009750 -16.3159+-0.0124 2.798576+-0.001532 -8.9212+-0.0049 0.168114+-0.000000 48.3333-73.5333 0.266124+-0.000058 11.5615+-0.0020 0.283209+-0.000000 6.3333-23.1333 0.193572+-0.000061 14.2755+-0.0031 0.425271+-0.000000 23.1333-48.3333 0.184649+-0.000163 14.6821+-0.0076 0.001317+-0.000000 73.5333-90.3333 1.804460+-0.001932 -4.9281+-0.0089
DDPM 33.30 7.7837+-0.1844 41.2021+-0.1844 0.9731+-0.0010 0.006599+-0.000113 0.000080+-0.000004 0.008816+-0.000195 6.370634+-0.085031 -15.8910+-0.1299 0.235900+-0.005620 12.6722+-0.2013 51.105551+-1.416591 -33.7590+-0.2365 23.034157+-0.819724 -26.8922+-0.2705 0.168114+-0.000000 48.3333-73.5333 0.435121+-0.009157 7.3876+-0.1786 0.283209+-0.000000 6.3333-23.1333 0.276556+-0.005804 11.2774+-0.1790 0.425271+-0.000000 23.1333-48.3333 0.284865+-0.005449 11.0101+-0.1739 0.001317+-0.000000 73.5333-90.3333 4.204208+-0.103543 -12.1174+-0.1917
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support