SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment

Hugging Face Daily Papers Papers
cad-to-image-alignment zero-shot feature-learning 9d-pose-estimation weakly-supervised geometry-aware

Summary

SUFLECA is a weakly-supervised framework for zero-shot CAD-to-image alignment, achieving state-of-the-art accuracy on ScanNet25k by scaling up geometry-grounded feature learning from pretrained visual representations.

CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, enabling applications in robotics and augmented reality. Recent zero-shot methods use visual foundation models to match image regions to CAD models, yet typically their correspondences are appearance-driven and degrade under occlusion or sim-to-real domain shift. To address these limitations, we introduce SUFLECA (Scaling Up Feature LEarning for CAD Alignment), a weakly-supervised framework for zero-shot CAD alignment with two key contributions. First, SUFLECA scales up geometry-grounded feature learning from pretrained visual representations through Normalized Object Coordinates (NOCs) supervision on 674K images spanning 12 real and synthetic datasets, learning compact geometry-aware features that generalize across domains. Second, we propose a geometrically consistent matching algorithm that establishes reliable one-to-one CAD-to-image correspondences. Together, these contributions enable accurate, sub-second alignment per object instance without iterative pose refinement. On ScanNet25k, SUFLECA achieves 33.4%/42.3% category/instance accuracy, outperforming, with a smaller computational footprint, the strongest zero-shot baseline by 10.3/12.2 percentage points and, for the first time on this benchmark, even surpassing fully supervised methods. Code is available at: https://github.com/snt-arg/SUFLECA
Original Article
View Cached Full Text

Cached at: 07/20/26, 09:41 AM

Paper page - SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment

Source: https://huggingface.co/papers/2607.15058

Abstract

CAD-to-imagealignmentaimstoestimateanobject’s9Dpose(rotation,translation,andanisotropicscale)fromasingleRGBimage,enablingapplicationsinroboticsandaugmentedreality.Recentzero-shotmethodsusevisualfoundationmodelstomatchimageregionstoCADmodels,yettypicallytheircorrespondencesareappearance-drivenanddegradeunderocclusionorsim-to-realdomainshift.Toaddresstheselimitations,weintroduceSUFLECA(ScalingUpFeatureLEarningforCADAlignment),aweakly-supervisedframeworkforzero-shotCADalignmentwithtwokeycontributions.First,SUFLECAscalesupgeometry-groundedfeaturelearningfrompretrainedvisualrepresentationsthroughNormalizedObjectCoordinates(NOCs)supervisionon674Kimagesspanning12realandsyntheticdatasets,learningcompactgeometry-awarefeaturesthatgeneralizeacrossdomains.Second,weproposeageometricallyconsistentmatchingalgorithmthatestablishesreliableone-to-oneCAD-to-imagecorrespondences.Together,thesecontributionsenableaccurate,sub-secondalignmentperobjectinstancewithoutiterativeposerefinement.OnScanNet25k,SUFLECAachieves33.4%/42.3%category/instanceaccuracy,outperforming,withasmallercomputationalfootprint,thestrongestzero-shotbaselineby10.3/12.2percentagepointsand,forthefirsttimeonthisbenchmark,evensurpassingfullysupervisedmethods.Codeisavailableat:https://github.com/snt-arg/SUFLECA

View arXiv pageView PDFGitHub1Add to collection

Get this paper in your agent:

hf papers read 2607\.15058

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.15058 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.15058 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.15058 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

SurGe: Improved Surface Geometry in Point Maps

Hugging Face Daily Papers

SurGe introduces a Neighborhood Attention Decoder and a reformulated scale-invariant gradient matching loss to improve local surface geometry accuracy in feedforward 3D reconstruction, particularly for thin structures. It achieves state-of-the-art average rank on zero-shot monocular geometry benchmarks, with better local point map and normal metrics.

FeatCal: Feature Calibration for Post-Merging Models

Hugging Face Daily Papers

FeatCal is a calibration method that reduces performance gaps in post-merging models by layer-wise weight updates without gradient descent, achieving superior results on CLIP and GLUE benchmarks with high sample efficiency.

Cross-scale Aligned Supervision for Training GANs

Hugging Face Daily Papers

This paper proposes CAT, a cross-scale aligned transformer that enforces consistency between intermediate and final GAN outputs to resolve trajectory misalignment, achieving state-of-the-art FID of 1.56 on ImageNet-256.