SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.05910 · 2022

Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report

arXiv · PDF · Open in the Atlas

Code that ran

11 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 8 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2211.05910.json · badge: /api/ran/2211.05910.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
eduardzamfir/ntire23-rtsr community (classifier label)
classifier basis not recorded on the link
11 ran · 3 no recorded run
FunctionStatusWhere it lives
conv Ran
ran; our contract draft was wrong, not the code
eduardzamfir/ntire23-rtsr/demo/models/modules/_imdn.py
code served (permissive licence) · get_code("0094b11c13bb8bf5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from collections import OrderedDict

torch.manual_seed(0)

ARGS = {
    'in_channels': 3,
    'out_channels': 64,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'bias': True,
    'mode': 'CBR',
    'negative_slope': 0.2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv_layer Ran
ran; our contract draft was wrong, not the code
eduardzamfir/ntire23-rtsr/demo/models/modules/_rfdn.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from liuzhu-cv/crmef, is pointer only (licence: NONE) · get_code("d3a234f32905b183")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from liuzhu-cv/crmef, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_model_activation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
eduardzamfir/ntire23-rtsr/demo/utils/model_summary.py
code served (permissive licence) · get_code("4b2444965efda665")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple model with Conv2d and Linear layers
class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.conv1 = nn.Conv2d(3, 8, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(8, 16, kernel_size=3, padding=1)
        self.linear = nn.Linear(16 * 4 * 4, 10)
    
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = torch.nn.functional.adaptive_avg_pool2d(x, (4, 4))
        x = x.view(x.size(0), -1)
        x = self.linear(x)
        return x

model = SimpleModel()

# input_res should be (channels, height, width)
input_res = (3, 8, 8)

# input_constructor is optional; we'll set it to None to use default behavior
input_constructor = None

ARGS = {
    "model": model,
    "input_res": input_res,
    "input_constructor": input_constructor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
import_srmodel Ran
ran on a synthesized input
eduardzamfir/ntire23-rtsr/demo/runtime_demo.py
code served (permissive licence) · get_code("2daa8d7e08b31c9e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import importlib
import sys
from types import ModuleType

# Create a mock module structure for models.test_team.arch
mock_arch_module = ModuleType('arch')

# Define a mock srmodel function
def mock_srmodel():
    return "srmodel_result"

# Add the function to the mock module
mock_arch_module.srmodel = mock_srmodel

# Create the models.test_team package structure
models_module = ModuleType('models')
test_team_module = ModuleType('test_team')
test_team_module.arch = mock_arch_module

models_module.test_team = test_team_module
sys.modules['models'] = models_module
sys.modules['models.test_team'] = test_team_module
sys.modules['models.test_team.arch'] = mock_arch_module

# Now define the arguments
ARGS = {
    'team': 'test_team'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
norm Ran
ran; our contract draft was wrong, not the code
eduardzamfir/ntire23-rtsr/demo/models/modules/_rfdn.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from jnjaby/DISCNet, is pointer only (licence: NONE) · get_code("b6a238bb90c0069b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from jnjaby/DISCNet, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pad Ran
ran; our contract draft was wrong, not the code
eduardzamfir/ntire23-rtsr/demo/models/modules/_rfdn.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from jnjaby/DISCNet, is pointer only (licence: NONE) · get_code("4a56ce1917d87f9b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from jnjaby/DISCNet, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pixel_unshuffle Ran
ran; our contract draft was wrong, not the code
eduardzamfir/ntire23-rtsr/demo/models/modules/_imdn.py
code served (permissive licence) · get_code("5d9b9713448d2a62")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 16, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small input tensor with shape (batch_size, channels, height, width)
# Using distinct sizes: batch=2, channels=4, height=8, width=6
input_tensor = torch.randn(2, 4, 8, 6)

# upscale_factor determines how the spatial dimensions are reduced
# and channels are increased (by factor of upscale_factor^2)
upscale_factor = 2

ARGS = {
    "input": input_tensor,
    "upscale_factor": upscale_factor,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 16, 4, 3) — shape (2, 16, 4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rtsrn Ran
ran on a synthesized input
eduardzamfir/ntire23-rtsr/demo/models/rtsrn.py
code served (permissive licence) · get_code("bf5b3866e660131d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned RealTimeSRNet. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "scale": 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type RealTimeSRNet — a RealTimeSRNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RealTimeSRNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
upsample_pixelshuffle Ran
ran; our contract draft was wrong, not the code
eduardzamfir/ntire23-rtsr/demo/models/modules/_imdn.py
code served (permissive licence) · get_code("7b75fe2c4c0e13be")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_channels': 64,
    'out_channels': 3,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'bias': True,
    'mode': '2R',
    'negative_slope': 0.2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
window_partition Ran
ran on a synthesized input
eduardzamfir/ntire23-rtsr/demo/models/swin2sr.py
code served (permissive licence) · get_code("a0b512b15c4525f7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Construct input tensor with shape (B, H, W, C)
# B=2 (batch), H=8 (height), W=8 (width), C=4 (channels)
# H and W must be divisible by window_size
x = torch.randn(2, 8, 8, 4)

# Window size must divide both H and W evenly
window_size = 4

ARGS = {
    "x": x,
    "window_size": window_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) — shape (8, 4, 4, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
window_reverse Ran
ran; our contract draft was wrong, not the code
eduardzamfir/ntire23-rtsr/demo/models/swin2sr.py
code served (permissive licence) · get_code("fb32094c6dbece71")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 8, 12, 6) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Define parameters
# We need windows of shape (num_windows*B, window_size, window_size, C)
# where num_windows = (H // window_size) * (W // window_size)

B = 2
H = 8
W = 12
window_size = 4
C = 6

# Calculate num_windows
num_windows_h = H // window_size  # 8 // 4 = 2
num_windows_w = W // window_size  # 12 // 4 = 3
num_windows = num_windows_h * num_windows_w  # 2 * 3 = 6

# Total number of windows across batch
total_windows = num_windows * B  # 6 * 2 = 12

# Create windows tensor
windows = torch.randn(total_windows, window_size, window_size, C)

ARGS = {
    'windows': windows,
    'window_size': window_size,
    'H': H,
    'W': W
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 8, 12, 6) — shape (2, 8, 12, 6) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_model_complexity_info Not yet run
unverified (harvested, no recorded run)
eduardzamfir/ntire23-rtsr/demo/utils/model_summary.py
code served (permissive licence) · get_code("91383555d4366904")
How it ran

no invocation recorded.

get_model_flops Not yet run
unverified (harvested, no recorded run)
eduardzamfir/ntire23-rtsr/demo/utils/model_summary.py
code served (permissive licence) · get_code("f01af9643c088013")
How it ran

no invocation recorded.

swin2sr Not yet run
unverified (harvested, no recorded run)
eduardzamfir/ntire23-rtsr/demo/models/swin2sr.py
code served (permissive licence) · get_code("60222f2fd164ff5d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 1 the same month, 9 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
window_reverse 227 other papers
69 dated earlier, 1 the same month, 155 later, 2 same year, order not determinable · 34 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 224 more not named here
pixel_unshuffle 10 other papers
4 dated earlier, 6 later
2008.13751 (2020-08)
Plug-and-Play Image Restoration with Deep Denoiser Prior
2110.03220 (2021-10)
Gradient Step Denoiser for convergent Plug-and-Play
2204.07114 (2022-04)
Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling
and 7 more not named here
upsample_pixelshuffle 10 other papers
4 dated earlier, 6 later
2008.13751 (2020-08)
Plug-and-Play Image Restoration with Deep Denoiser Prior
2109.14573 (2021-09)
Towards Flexible Blind JPEG Artifacts Removal
2110.03220 (2021-10)
Gradient Step Denoiser for convergent Plug-and-Play
and 7 more not named here
conv 9 other papers
4 dated earlier, 5 later
2008.13751 (2020-08)
Plug-and-Play Image Restoration with Deep Denoiser Prior
2109.14573 (2021-09)
Towards Flexible Blind JPEG Artifacts Removal
2203.05568 (2022-03)
Unfolded Deep Kernel Estimation for Blind Image Super-resolution
and 6 more not named here
norm 5 other papers
4 dated earlier, 1 later
1809.00219 (2018-09)
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
2009.11551 (2020-09)
Residual Feature Distillation Network for Lightweight Image Super-Resolution
2104.09556 (2021-04)
Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network
and 2 more not named here
pad 5 other papers
4 dated earlier, 1 later
1809.00219 (2018-09)
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
2009.11551 (2020-09)
Residual Feature Distillation Network for Lightweight Image Super-Resolution
2104.09556 (2021-04)
Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network
and 2 more not named here
get_model_activation 4 other papers
2 dated earlier, 2 later
2205.05675 (2022-05)
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
2207.13784 (2022-07)
AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing
2303.09472 (2023-03)
DiffIR: Efficient Diffusion Model for Image Restoration
and 1 more not named here
get_model_complexity_info 4 other papers
2 dated earlier, 2 later
2205.05675 (2022-05)
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
2207.13784 (2022-07)
AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing
2303.09472 (2023-03)
DiffIR: Efficient Diffusion Model for Image Restoration
and 1 more not named here
conv_layer 3 other papers
2 dated earlier, 1 later
1909.10692 (2019-09)
Deformable Non-local Network for Video Super-Resolution
2009.11551 (2020-09)
Residual Feature Distillation Network for Lightweight Image Super-Resolution
2308.03979 (2023-08)
PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints. In this Mobile AI challenge, we address this problem and propose the participants to design an efficient quantized image super-resolution solution that can demonstrate a real-time performance on mobile NPUs. The participants were provided with the DIV2K dataset and trained INT8 models to do a high-quality 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU capable of accelerating quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 60 FPS rate when reconstructing Full HD resolution images. A detailed description of all models developed in the challenge is provided in this paper.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2211.05910")
get_code_for_paper("2211.05910")
have("2211.05910")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2211.05910.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2211.05910.svg)](https://syntology.ai/paper/2211.05910)

Connect an agent — have() is free.