Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models

Hugging Face Daily Papers Papers
test-time-adaptation 3d-vision geometric-consistency lora vision-foundation-models multi-view-geometry

Summary

Presents Self-Geometry, a plug-and-play test-time adaptation pipeline that enforces explicit multi-view geometric constraints using 2D pixel correspondences to improve geometrically consistent 3D vision foundation models.

Recent Vision Foundation Models (VFMs) predict depth, camera pose, and pointmap in a single forward pass without per-scene optimization, achieving strong generalization. However, enforcing explicit multi-view geometric consistency, e.g., through bundle adjustment, is computationally costly and is thus not imposed during VFM pretraining, so such inconsistency can arise. To address this, implicit self-consistency derived from model outputs (e.g., pointmaps, features), though enforced at test-time in prior work, delivers inherently limited performance gain, especially on scenes where the pretrained VFM is highly inaccurate. In contrast to this implicit signal, we propose Self-Geometry, a plug-and-play test-time adaptation pipeline that directly imposes explicit multi-view geometric constraints using 2D pixel correspondences as pseudo ground-truth. Our proposed Self-Geometry consists of Geometric Disentanglement Optimization, which combines Multi-View Consistency and Epipolar Consistency losses with Gradient Disentanglement to prevent gradient conflict; Frame Angular-Neighbor, a view sampler based on SO(3) geodesic distances for lightly imposing these constraints; and Lightweight TTA, which adapts VFMs via LoRA. Our method achieves consistent improvements in both pose and geometry estimation across six VFMs (VGGT, π^3, DA3-Giant/Large/Base/Small) and four benchmarks (7Scenes, ETH3D, ScanNet++, HiRoom).
Original Article
View Cached Full Text

Cached at: 08/13/26, 03:33 PM

Paper page - Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models

Source: https://huggingface.co/papers/2608.10708

Abstract

Self-Geometry improves vision foundation model predictions by enforcing explicit multi-view geometric constraints via test-time adaptation with LoRA, disentangled losses, and angular neighbor sampling.

RecentVision Foundation Models(VFMs) predict depth, camera pose, and pointmap in a single forward pass without per-scene optimization, achieving strong generalization. However, enforcing explicitmulti-view geometric consistency, e.g., throughbundle adjustment, is computationally costly and is thus not imposed during VFM pretraining, so such inconsistency can arise. To address this, implicit self-consistency derived from model outputs (e.g.,pointmaps, features), though enforced at test-time in prior work, delivers inherently limited performance gain, especially on scenes where the pretrained VFM is highly inaccurate. In contrast to this implicit signal, we proposeSelf-Geometry, a plug-and-play test-time adaptation pipeline that directly imposes explicit multi-view geometric constraints using 2D pixel correspondences as pseudo ground-truth. Our proposedSelf-Geometryconsists ofGeometric Disentanglement Optimization, which combines Multi-View Consistency andEpipolar Consistency losses withGradient Disentanglementto prevent gradient conflict;Frame Angular-Neighbor, a view sampler based onSO(3) geodesic distancesfor lightly imposing these constraints; andLightweight TTA, which adapts VFMs viaLoRA. Our method achieves consistent improvements in both pose and geometry estimation across six VFMs (VGGT, π^3, DA3-Giant/Large/Base/Small) and four benchmarks (7Scenes, ETH3D, ScanNet++, HiRoom).

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2608\.10708

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/2608.10708 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.10708 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.10708 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

Towards Consistent Video Geometry Estimation

Hugging Face Daily Papers

ViGeo is a transformer-based foundation model that recovers dense and consistent 3D geometry from videos using dynamic chunking attention and a completion-based data refinement framework, achieving state-of-the-art performance across multiple tasks.

SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space

Hugging Face Daily Papers

This paper proposes SG-WAM, a self-guided framework for learning geometry-aware action-conditioned world models directly in policy-derived representation space. It achieves state-of-the-art success rates on LIBERO and LIBERO-Plus benchmarks, outperforming strong baselines in real-world evaluations.

Unified Panoramic Geometry Estimation via Multi-View Foundation Models

Hugging Face Daily Papers

PaGeR adapts the multi-view perspective foundation model Depth Anything 3 to predict scale-invariant and metric depth, surface normals, and sky segmentation from a single equirectangular image, using a fixed cubemap representation that keeps VRAM and runtime constant. The paper also releases the ZüriPano and PanoInfinigen datasets.

Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence

Hugging Face Daily Papers

This paper introduces a post-training framework that leverages 3D priors from SAM3D to improve semantic correspondence in 2D foundation features, addressing issues like left-right confusion and repeated parts. The method uses instance-specific 3D reconstruction without pose annotations or spherical geometry shortcuts.