Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

Self-Geometry: Test-Time Adaptation Boosts 3D Vision Foundation Models Without Ground Truth

AI By Crimson AI Hugging Face Papers 13 August 2026 · 00:00 15 views
Share: X Telegram

A new plug-and-play method, Self-Geometry, enforces explicit multi-view geometric constraints during test-time adaptation, improving pose and geometry estimation across six 3D vision foundation models and four benchmarks.

Self-Geometry: Test-Time Adaptation Boosts 3D Vision Foundation Models Without Ground Truth

Key points

Recent Vision Foundation Models (VFMs) predict depth, camera pose, and pointmaps in a single forward pass, achieving strong generalization without per-scene optimization. However, they do not enforce explicit multi-view geometric consistency during pretraining, as doing so (e.g., via bundle adjustment) is computationally expensive. This can lead to inconsistencies in predictions.

To address this, researchers from CMLab Korea propose Self-Geometry, a plug-and-play test-time adaptation (TTA) pipeline that directly imposes explicit multi-view geometric constraints using 2D pixel correspondences as pseudo ground-truth. Unlike prior TTA methods that rely on implicit self-consistency from model outputs—which offer limited gains where the pretrained VFM is most inaccurate—Self-Geometry supervises with explicit geometry.

The method comprises three key components: Geometric Disentanglement Optimization, which combines Multi-View Consistency and Epipolar Consistency losses with Gradient Disentanglement to prevent gradient conflicts; Frame Angular-Neighbor, a view sampler based on SO(3) geodesic distances; and Lightweight TTA, which adapts VFMs via LoRA. The adaptation completes in a few minutes on a single GPU.

Experiments show consistent improvements in both pose and geometry estimation across six VFMs (VGGT, π³, DA3-Giant/Large/Base/Small) and four benchmarks (7Scenes, ETH3D, ScanNet++, HiRoom). The project page offers interactive side-by-side comparisons.

ModelBenchmarkImprovement
VGGT7Scenes, ETH3D, ScanNet++, HiRoomConsistent mean improvement
π³7Scenes, ETH3D, ScanNet++, HiRoomConsistent mean improvement
DA3-Giant/Large/Base/Small7Scenes, ETH3D, ScanNet++, HiRoomConsistent mean improvement
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

0
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

0
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

0