SCCM: Spherically Consistent Coarse Matching for ERP Dense Feature Correspondence

arXiv:2609.36545 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-10-03

Project page: https://gandanlee.github.io/sccm

Terminology

• Ablation — 19× in this paper · explained in 1 episode
• Transformer — 14× in this paper · explained in 2 episodes
• Spherically Consistent Coarse Matching — 12× in this paper
• AUC — 11× in this paper · explained in 2 episodes
• Log-Area Correction — 10× in this paper
• Accuracy — 9× in this paper · explained in 1 episode
• Tangent-Plane Bias — 9× in this paper
• Area-Aware Covisibility — 6× in this paper
• Calibration — 4× in this paper · explained in 7 episodes
• Spherical Positional Attention — 4× in this paper
• Angular Error — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Additivity — 1× in this paper · explained in 1 episode
• Anisotropy — 1× in this paper · explained in 3 episodes
• Domain Shift — 1× in this paper · explained in 4 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Joint 2D-3D-Semantic Data for Indoor Scene Understanding
• SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE
• DINOv2: Learning Robust Visual Features without Supervision
• Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond
• RoFormer: Enhanced Transformer with Rotary Position Embedding
• EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\circ$
• Dense360: Dense Understanding from Omnidirectional Panoramas

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