Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching

arXiv:2610.12421 · cs.CV, cs.LG · Submitted 2026-10-08 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/luping-liu/FreeMatching

Project page: https://haofeixu.github.io/unimatch

Terminology

• Benchmark — 23× in this paper · explained in 2 episodes
• Alignment — 22× in this paper · explained in 1 episode
• Optical Flow — 22× in this paper · explained in 2 episodes
• Consistency — 13× in this paper · explained in 3 episodes
• Adaptation — 12× in this paper · explained in 1 episode
• Iterative Refinement — 12× in this paper · explained in 3 episodes
• Transformer — 10× in this paper · explained in 2 episodes
• Generalization — 8× in this paper · explained in 13 episodes
• Fidelity — 7× in this paper · explained in 2 episodes
• Distillation — 5× in this paper · explained in 2 episodes
• Foundation Model — 5× in this paper · explained in 3 episodes
• Foundation Models — 5× in this paper · explained in 7 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Robustness — 4× in this paper · explained in 5 episodes
• AUC — 3× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Semantic Alignment — 3× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Exponential Moving Average (EMA) — 2× in this paper · explained in 2 episodes
• Feature Extraction — 2× in this paper · explained in 2 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 3 episodes
• Joint Attention — 2× in this paper · explained in 2 episodes
• Mask Generation — 2× in this paper · explained in 2 episodes
• Reconstruction Error — 2× in this paper · explained in 2 episodes
• Two-stage training — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• Angular Error — 1× in this paper · explained in 1 episode
• Composite Loss Function — 1× in this paper · explained in 2 episodes
• End-Point Error — 1× in this paper
• Human Mean Opinion Score — 1× in this paper
• Latent Representation — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Mean Squared Error — 1× in this paper
• Provenance — 1× in this paper · explained in 4 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
• Qwen-Image Technical Report
• Seedream 4.0: Toward Next-generation Multimodal Image Generation
• DINOv3
• DINOv2: Learning Robust Visual Features without Supervision
• Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors
• BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
• PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking
• FlowNet: Learning Optical Flow with Convolutional Networks
• ViPE: Video Pose Engine for 3D Geometric Perception
• SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
• Qwen3-VL Technical Report
• SAM 3: Segment Anything with Concepts

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