# Not All Pixels Are Equal: Confidence-Guided Attention for Feature Matching

arXiv: https://arxiv.org/abs/2505.02161 · HTML: https://mlsanity.com/paper/2505.02161/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 45 of its 56 references that are in the map.
- First posted on arXiv 4 May 2025.

## Builds on (most cited first, 30 of 45)

- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [Splatter Image: Ultra-Fast Single-View 3D Reconstruction](https://mlsanity.com/paper/2312.13150/) (2023)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https://mlsanity.com/paper/2412.12392/) (2024)
- [Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM](https://mlsanity.com/paper/2304.14377/) (2023)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [MatchFormer: Interleaving Attention in Transformers for Feature Matching](https://mlsanity.com/paper/2203.09645/) (2022)
- [Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed](https://mlsanity.com/paper/2403.04765/) (2024)
- [XFeat: Accelerated Features for Lightweight Image Matching](https://mlsanity.com/paper/2404.19174/) (2024)
- [Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions](https://mlsanity.com/paper/2004.10566/) (2020)
- [Detector-Free Structure from Motion](https://mlsanity.com/paper/2306.15669/) (2023)
- [DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching](https://mlsanity.com/paper/2308.08479/) (2023)
- [Repeatability Is Not Enough: Learning Affine Regions via Discriminability](https://mlsanity.com/paper/1711.06704/) (2017)
- [WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments](https://mlsanity.com/paper/2504.03886/) (2025)
- [Light3R-SfM: Towards Feed-forward Structure-from-Motion](https://mlsanity.com/paper/2501.14914/) (2025)
- [TopicFM: Robust and Interpretable Topic-Assisted Feature Matching](https://mlsanity.com/paper/2207.00328/) (2022)

## Abstract (arXiv)

Semi-dense feature matching methods have been significantly advanced by leveraging attention mechanisms to extract discriminative descriptors. However, most existing approaches treat all pixels equally during attention computations, which can potentially introduce noise and redundancy from irrelevant regions. To address this issue, we propose a confidence-guided attention that adaptively prunes attention weights for each pixel based on precomputed matching confidence maps. These maps are generated by evaluating the mutual similarity between feature pairs extracted from the backbone, where high confidence indicates a high potential for matching. Then the attention is refined through two steps: (1) a confidence-guided bias is introduced to adaptively adjust the attention distributions for each query pixel, avoiding irrelevant interactions between non-overlap pixels; (2) the corresponding confidence map is additionally employed to rescale value features during feature aggregation, attenuating the influence of uncertain regions. Moreover, a classification loss is introduced to encourage the backbone's features to discriminate between matchable and non-matchable regions. Extensive experiments on three benchmarks demonstrate that the proposal outperforms existing state-of-the-art methods.