SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.12102 · ICCV · 2021

FOVEA: Foveated Image Magnification for Autonomous Navigation

Deva Ramanan, Mengtian Li, Chittesh Thavamani, Nicolas Cebron

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 0 failures of our instrument; 1 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/2108.12102.json · badge: /api/ran/2108.12102.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
tchittesh/fovea canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
add_config_args Ran
ran on a synthesized input
tchittesh/fovea/fovea/utils/config.py
code served (permissive licence) · get_code("e0e452f67f238381")
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 ArgumentParser. 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 argparse
import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal ArgumentParser
parser = argparse.ArgumentParser()

# The function add_config_args only takes a parser as argument
# It doesn't actually use the parser in any complex way beyond adding argument groups
# So we just need to pass a valid ArgumentParser instance

ARGS = {
    'parser': parser
}
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 ArgumentParser — a ArgumentParser output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ArgumentParser 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
make2DGaussian Ran
ran on a synthesized input
tchittesh/fovea/fovea/models/grid_generator.py
code served (permissive licence) · get_code("447345f08cbf70b8")
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 ndarray, ndim 2, dtype family float, shape (16, 16) 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 numpy as np

# Analyze the function:
# - size: int, used as length of side of square (passed to np.arange)
# - fwhm: int/float, default=3, used in division (optional parameter)
# - center: None or tuple/list of 2 elements [x0, y0], used for indexing (optional parameter)

# Test with a basic configuration
size = 16
fwhm = 3
center = (8, 8)

ARGS = {
    "size": size,
    "fwhm": fwhm,
    "center": center
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (16, 16) — shape (16, 16) 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
overlay_grid Ran
ran on a synthesized input
tchittesh/fovea/fovea/utils/vis.py
code served (permissive licence) · get_code("5b589e05318b1964")
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 int, shape (2, 4, 512, 512) 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)

# The function expects a tensor with shape (batch, channels, height, width)
# It accesses imgs[0, 0, ...], imgs[0, 1:3, ...], so we need at least:
# - batch size >= 1
# - channels >= 3
# - height and width >= 6 (to accommodate the slicing with spacing=100)
# Create a tensor with shape (2, 4, 512, 512) to have enough space
imgs = torch.zeros(2, 4, 512, 512, dtype=torch.uint8)

ARGS = {
    "imgs": imgs
}
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 int, shape (2, 4, 512, 512) — shape (2, 4, 512, 512) 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
make1DGaussian Not yet run
unverified (harvested, no recorded run)
tchittesh/fovea/fovea/models/grid_generator.py
code served (permissive licence) · get_code("154960a78156be34")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

Efficient processing of high-resolution video streams is safety-critical for many robotics applications such as autonomous driving. Image downsampling is a commonly adopted technique to ensure the latency constraint is met. However, this naive approach greatly restricts an object detector's capability to identify small objects. In this paper, we propose an attentional approach that elastically magnifies certain regions while maintaining a small input canvas. The magnified regions are those that are believed to have a high probability of containing an object, whose signal can come from a dataset-wide prior or frame-level prior computed from recent object predictions. The magnification is implemented by a KDE-based mapping to transform the bounding boxes into warping parameters, which are then fed into an image sampler with anti-cropping regularization. The detector is then fed with the warped image and we apply a differentiable backward mapping to get bounding box outputs in the original space. Our regional magnification allows algorithms to make better use of high-resolution input without incurring the cost of high-resolution processing. On the autonomous driving datasets Argoverse-HD and BDD100K, we show our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning. Additionally, building on top of the previous state-of-the-art in streaming detection, our method sets a new record for streaming AP on Argoverse-HD (from 17.8 to 23.0 on a GTX 1080 Ti GPU), suggesting that it has achieved a superior accuracy-latency tradeoff. * denotes equal contribution.

For agents

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

get_harvested_code_for_paper("2108.12102")
get_code_for_paper("2108.12102")
have("2108.12102")

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

curl https://syntology.ai/api/ran/2108.12102.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.12102.svg)](https://syntology.ai/paper/2108.12102)

Connect an agent — have() is free.