Patch Matching
2개 벤치마크 · 논문 99편 · 이 태스크의 논문 보기 →
Benchmarks
Brown Dataset
HPatches
Most implemented
Working hard to know your neighbor's margins: Local descriptor learning loss
On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location
Rotation equivariant vector field networks
IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching
Attention Concatenation Volume for Accurate and Efficient Stereo Matching
Continuous 3D Label Stereo Matching using Local Expansion Moves
Papers
3D-GIMP: When 3D Gaussian Inpainting Meets PatchMatch
Recent advances in 3D scene editing have leveraged iterative diffusion models to update input views. However, this process is computationally expensive and struggles to produce sharp details. Meanwhile, ``hallucination d…
3D Reconstruction3D scene EditingPatch MatchingNIFTY: a Non-Local Image Flow Matching for Texture Synthesis
This paper addresses the problem of exemplar-based texture synthesis. We introduce NIFTY, a hybrid framework that combines recent insights on diffusion models trained with convolutional neural networks, and classical pat…
Patch MatchingReproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction
Visual Document Retrieval (VDR) is an emerging research area that focuses on encoding and retrieving document images directly, bypassing the dependence on Optical Character Recognition (OCR) for document search. A recent…
Optical Character RecognitionOptical Character Recognition (OCR)Patch MatchingRetrieval+1MicroFlow: Domain-Specific Optical Flow for Ground Deformation Estimation in Seismic Events
Dense ground displacement measurements are crucial for geological studies but are impractical to collect directly. Traditionally, displacement fields are estimated using patch matching on optical satellite images from di…
GeophysicsOptical Flow EstimationPatch MatchingThe Marine Debris Forward-Looking Sonar Datasets
Sonar sensing is fundamental for underwater robotics, but limited by capabilities of AI systems, which need large training datasets. Public data in sonar modalities is lacking. This paper presents the Marine Debris Forwa…
DiversityObjectobject-detectionObject Detection+2Fence Theorem: Preprocessing is Dual-Objective Semantic Structure Isolator in 3D Anomaly Detection
3D anomaly detection (AD) is prominent but difficult due to lacking a unified theoretical foundation for preprocessing design. We establish the Fence Theorem, formalizing preprocessing as a dual-objective semantic isolat…
3D Anomaly DetectionAnomaly DetectionMathematical ProofsPatch Matching+1