Papers with Code 아카이브

Image Matching

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

4

평가표

2

보존된 평가 기록

18

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/ActiveVisionLab/ANCNet

공식 코드

Correspondence Networks with Adaptive Neighbourhood Consensus

https://github.com/CodeJjang/multiscale-attention-patch-matching

공식 코드

Attention-Based Multimodal Image Matching

https://github.com/CompVis/cleandift

공식 코드

CleanDIFT: Diffusion Features without Noise

https://github.com/DagnyT/hardnet

공식 코드

Working hard to know your neighbor's margins: Local descriptor learning loss

https://github.com/Easonyesheng/A2PM-MESA

공식 코드

MESA: Effective Matching Redundancy Reduction by Semantic Area Segmentation

https://github.com/EvelynFan/FAU

공식 코드

Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution

https://github.com/GuiyuZhao/SGOR

공식 코드

SGOR: Outlier Removal by Leveraging Semantic and Geometric Information for Robust Point Cloud Registration

https://github.com/HDETR/H-Deformable-DETR

공식 코드

DETRs with Hybrid Matching

https://github.com/HDETR/H-Deformable-DETR-mmdet

공식 코드

DETRs with Hybrid Matching

https://github.com/HDETR/H-Detic-LVIS

공식 코드

DETRs with Hybrid Matching

https://github.com/HDETR/H-PETR-3D

공식 코드

DETRs with Hybrid Matching

https://github.com/HDETR/H-PETR-Pose

공식 코드

DETRs with Hybrid Matching

https://github.com/JiYuanFeng/MCTrans

공식 코드

Multi-Compound Transformer for Accurate Biomedical Image Segmentation

https://github.com/JingfenQiao/ColPali-Reproducibility

공식 코드

Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction

https://github.com/Junyi42/geoaware-sc

공식 코드

Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence

https://github.com/Junyi42/sd-dino

공식 코드

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

https://github.com/KU-CVLAB/CATs-PlusPlus

공식 코드

CATs++: Boosting Cost Aggregation with Convolutions and Transformers

https://github.com/KU-CVLAB/NeMF

공식 코드

Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence

https://github.com/Mathux/FROT

공식 코드

Feature Robust Optimal Transport for High-dimensional Data

https://github.com/QianWangX/VidSeg_diffusion

공식 코드

Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models

https://github.com/RobertLuo1/HDC

공식 코드

CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation

https://github.com/Seokju-Cho/Volumetric-Aggregation-Transformer

공식 코드

Cost Aggregation Is All You Need for Few-Shot Segmentation

https://github.com/Shaoli-Huang/SnapMix

공식 코드

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data

https://github.com/The-Learning-And-Vision-Atelier-LAVA/PoSFeat

공식 코드

Decoupling Makes Weakly Supervised Local Feature Better

https://github.com/TimoBolkart/TEMPEH

공식 코드

Instant Multi-View Head Capture through Learnable Registration

https://github.com/Visual-AI/Semantic-Correspondence

공식 코드

Semantic Correspondence: Unified Benchmarking and a Strong Baseline

https://github.com/YangShenSJTUs/ReIDCorresStructure

공식 코드

Person Re-identification with Correspondence Structure Learning

https://github.com/adlsn/surfpatch

공식 코드

SurfPatch: Enabling Patch Matching for Exploratory Stream Surface Visualization

https://github.com/ai-it-avs/robustmat

공식 코드

RobustMat: Neural Diffusion for Street Landmark Patch Matching under Challenging Environments

https://github.com/aiart-hdu/matebit

공식 코드

Masked and Adaptive Transformer for Exemplar Based Image Translation

https://github.com/aim-uofa/diffews

공식 코드

Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation

https://github.com/air-discover/omni-pq

공식 코드

From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds

https://github.com/alibaba-mmai-research/HyRSM

공식 코드

Hybrid Relation Guided Set Matching for Few-shot Action Recognition

https://github.com/alibaba-mmai-research/hyrsmplusplus

공식 코드

HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition

https://github.com/alijavidani/local_global_representation_learning

공식 코드

Patch-Wise Self-Supervised Visual Representation Learning: A Fine-Grained Approach

https://github.com/alxead/sfc

공식 코드

Semantic-Aware Fine-Grained Correspondence

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.