Gauge-Equivariant Attention for Rotation-Stable 360 Scene Understanding

arXiv:2609.31755 · cs.CV, cs.GR · Submitted 2026-09-23 · Read on arXiv

cs.CV, cs.GR

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/Jaywalk18/equissl-release

Terminology

• Transformer — 26× in this paper · explained in 2 episodes
• Ablation — 23× in this paper · explained in 1 episode
• Consistency — 13× in this paper · explained in 3 episodes
• Distillation — 12× in this paper · explained in 2 episodes
• Robustness — 11× in this paper · explained in 5 episodes
• Fine-Tuning — 10× in this paper · explained in 5 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Gauge Dependence — 7× in this paper · explained in 2 episodes
• National University of Defense Technology — 5× in this paper
• Alignment — 4× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 4× in this paper
• European Conference on Computer Vision — 4× in this paper
• Holonomy — 4× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 4× in this paper
• Provenance — 4× in this paper · explained in 3 episodes
• Self-Supervised Learning — 4× in this paper · explained in 7 episodes
• ACM Transactions on Graphics — 3× in this paper
• Angular Error — 3× in this paper · explained in 1 episode
• Zero-Shot Transfer — 3× in this paper · explained in 3 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Data Augmentation — 2× in this paper · explained in 7 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• International Conference on Machine Learning — 2× in this paper
• Trace — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Agnostic Learning — 1× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Joint 2D-3D-Semantic Data for Indoor Scene Understanding
• Grounding inductive biases in natural images:invariance stems from variations in data
• Does equivariance matter at scale?
• HEAL-SWIN: A Vision Transformer On The Sphere
• Equivariant Contrastive Learning
• Ensembles provably learn equivariance through data augmentation
• DINOv3
• Open Panoramic Segmentation
• SO3UFormer: Learning Intrinsic Spherical Features for Rotation-Robust Panoramic Dense Prediction
• Spherical View Synthesis for Self-Supervised 360 Depth Estimation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models