SPEED+ Pose Estimator β sim-to-real study checkpoints
Direct 6DoF pose regression (ResNet-50 + MLP head) trained only on synthetic
SPEED+ imagery: the checkpoints behind a study of what transfers across the
synthetic-to-real gap. Eight are the published arms; nine more are the
post-review runs. results/checkpoints.json in the repository lists all
seventeen with their sha256.
The study itself reproduces without the weights; see the repository.
These are not competitive weights. They are the experimental arms of a study, and exist so that its table can be regenerated rather than taken on trust.
Paper: Nikolay Dolgov, Unreasonable Confidence from Simulator Misspecification: Directional Robustness on the SPEED+ Sim-to-Real Benchmark, arXiv:2611.20321.
Code, configs and the reproduction script: https://github.com/lokindoo/spacecraft-pose-estimation
These files are a mirror of the archived, citable copy on Zenodo: 10.5281/zenodo.24140385. The two hold byte-identical files; cite the DOI.
Checkpoints
The selection rule, applied uniformly, is the checkpoint with the best synthetic validation rotation error among those saved on even epochs. No real-domain measurement informed the choice.
SHA256SUMS, next to the weights here and on Zenodo, lists each file's hash.
The same hashes appear in results/checkpoints.json, whose checkpoint field
gives each file's original name from training. The repository's scripts accept
either name.
To download all seventeen into one directory and regenerate the results table:
hf download lkid08/spacecraft-pose-estimation --local-dir checkpoints
python scripts/reproduce_table.py --from-checkpoints checkpoints
Results table
Ten files, behind the results table below.
| File | Backbone | Augmentation | Seed | Trained on |
|---|---|---|---|---|
frozen_no_aug_seed42.pt |
frozen | β | 42 | Colab |
frozen_aug_seed42.pt |
frozen | β | 42 | Colab |
frozen_aug_seed43.pt |
frozen | β | 43 | Apple M5 |
frozen_aug_seed44.pt |
frozen | β | 44 | Apple M5 |
unfrozen_no_aug_seed42.pt |
layer 4 trainable | β | 42 | Colab |
unfrozen_no_aug_seed43.pt |
layer 4 trainable | β | 43 | Colab |
unfrozen_no_aug_seed44.pt |
layer 4 trainable | β | 44 | Colab |
unfrozen_aug_seed42.pt |
layer 4 trainable | β | 42 | Colab |
unfrozen_aug_seed43.pt |
layer 4 trainable | β | 43 | Colab |
unfrozen_aug_seed44.pt |
layer 4 trainable | β | 44 | Colab |
Augmentation ablation
Seven post-review files, all with layer 4 trainable, trained on an Apple M5.
| File | Augmentation | Seed |
|---|---|---|
unfrozen_aug_no_blur_noise_seed42.pt |
arm A: full stack minus blur and noise | 42 |
unfrozen_aug_no_blur_noise_seed43.pt |
arm A: full stack minus blur and noise | 43 |
unfrozen_aug_no_blur_noise_seed44.pt |
arm A: full stack minus blur and noise | 44 |
unfrozen_aug_jitter_gamma_seed42.pt |
arm B: jitter, gamma and erasing only | 42 |
unfrozen_aug_jitter_gamma_seed43.pt |
arm B: jitter, gamma and erasing only | 43 |
unfrozen_aug_jitter_gamma_seed44.pt |
arm B: jitter, gamma and erasing only | 44 |
control_unfrozen_aug_seed42.pt |
control: full stack, rerun on the ablation's hardware | 42 |
Results
E_T range-normalised; E_R geodesic, in radians. The chance level for E_R is 2.207 rad, the error of a uniformly random orientation guess. Read the errors as distance below that rather than as absolute magnitudes.
| Backbone | Aug. | Synth E_T | Synth E_R | Lightbox E_T | Lightbox E_R | Sunlamp E_T | Sunlamp E_R |
|---|---|---|---|---|---|---|---|
| frozen | β | 0.066 | 1.053 | 0.151 | 1.752 | 0.253 | 2.048 |
| frozen | β | 0.073Β±0.002 | 1.185Β±0.019 | 0.121Β±0.005 | 1.708Β±0.031 | 0.304Β±0.024 | 1.876Β±0.010 |
| layer 4 | β | 0.036Β±0.002 | 0.317Β±0.010 | 0.169Β±0.027 | 1.166Β±0.018 | 0.311Β±0.036 | 1.534Β±0.075 |
| layer 4 | β | 0.042Β±0.002 | 0.322Β±0.027 | 0.150Β±0.017 | 0.987Β±0.010 | 0.355Β±0.081 | 1.468Β±0.119 |
The frozen un-augmented arm is single-seed; the other arms are mean Β± s.d. over seeds 42/43/44. Frozen augmented seeds 43 and 44 were trained on an Apple M5, the rest on Colab.
Inference
The model code is in the repository:
pip install git+https://github.com/lokindoo/spacecraft-pose-estimation.
import torch
from huggingface_hub import hf_hub_download
from PIL import Image
from speedplus_pose.model import SpacecraftPoseEstimator
from speedplus_pose.normalisation import TranslationNormaliser
from speedplus_pose.transforms import build_eval_transform
repo = "lkid08/spacecraft-pose-estimation"
hf_hub_download(repo, "config.json") # the file the Hub counts downloads by
path = hf_hub_download(repo, "unfrozen_aug_seed42.pt")
checkpoint = torch.load(path, weights_only=False, map_location="cpu")
model = SpacecraftPoseEstimator()
model.load_state_dict(checkpoint["model_state_dict"])
model.eval()
# Translation targets were z-scored during training; the constants travel with
# the checkpoint. Skipping this step silently produces nonsense positions.
normaliser = TranslationNormaliser(checkpoint["train_means"], checkpoint["train_stds"])
image = Image.open("img000001.jpg") # SPEED+ grayscale, any resolution
tensor = build_eval_transform()(image) # -> 3x320x512, ImageNet-normalised
with torch.no_grad():
output = model(tensor.unsqueeze(0))
translation = normaliser.remove(output[:, :3]) # metres, camera frame
quaternion = output[:, 3:]
quaternion = quaternion / quaternion.norm(dim=1, keepdim=True) # scalar-first, unit
print(translation, quaternion)
Note the asymmetry. The translation half must be un-normalised; the quaternion half must not, since it is trained raw and unit-normalised. Passing the quaternion through the de-normaliser mangles every orientation in a way that still looks plausible.
One file stores no constants: frozen_no_aug_seed42.pt predates the code that
saved them, so the example raises KeyError on it. Every arm trained on the
same subset, and the other sixteen files store identical constants; take them
from any of those. normalisation.constants_for_checkpoint recomputes them
from the SPEED+ training labels instead.
Intended use
Intended for research on sim-to-real transfer, domain-gap benchmarking on SPEED+, uncertainty-quantification studies under distribution shift, and as a reproducible baseline for direct pose regression.
Not intended for any operational use. Explicitly:
This is a research artifact, not flight software. It has no verification, validation, qualification, or testing appropriate to a spaceflight system, and must not be used in a real rendezvous, proximity-operations, docking, or servicing system.
Limitations
- Real-domain accuracy is poor in absolute terms. The best arm's rotation error on sunlamp (1.47 rad β 84Β°) retains only ~36% of its synthetic skill.
- The model does not know when it is wrong. Conformal regions calibrated to 90% on synthetic data cover 9β15% of rotation errors on real domains, so confidence is not informative under the shift and predictions arrive as confidently wrong as they do correct.
- Augmentation is directional. The photometric stack is a poor model of both real domains and a markedly less poor one of the diffuse, lightbox-like case. It improves lightbox on every seed, and does not move sunlamp's harsh directional light beyond seed-to-seed variation.
- Trained on one target only, the Tango spacecraft. This is not a general-purpose spacecraft pose estimator.
- Fixed input geometry: 320Γ512 grayscale, one camera's intrinsics.
- Direct regression relies on coarse global shape, so it degrades less than keypoint+PnP pipelines across the gap. That is a property of the method class rather than a sign that these weights are robust.
Training data
SPEED+ synthetic split only: 28,000 training and 2,000 validation images, downscaled to 320Γ512 grayscale. No real image influenced training, tuning, or checkpoint selection; the lightbox (6,740) and sunlamp (2,791) sets are used strictly as held-out tests.
Dataset licence
The weights are derived from SPEED+, which is licensed under Creative Commons Attribution 4.0 International.
The ResNet-50 backbone was initialised from torchvision's ImageNet-pretrained
weights (IMAGENET1K_V2), which may carry their own terms.
SPEED+ itself is not redistributed here, in any form.
Citation
@article{dolgov2026unreasonable,
title = {Unreasonable Confidence from Simulator Misspecification: Directional
Robustness on the {SPEED+} Sim-to-Real Benchmark},
author = {Dolgov, Nikolay},
journal = {arXiv preprint arXiv:2611.20321},
year = {2026},
doi = {10.48550/arXiv.2611.20321}
}
CITATION.cff in the repository has the same, with the DOIs of each archived
release. Cite the SPEED+ dataset (Park et al., 2022) alongside this work.
- Downloads last month
- 22