paper-with-me

Papers

Dual Task Learning by Leveraging Both Dense Correspondence and Mis-Correspondence for Robust Change Detection With Imperfect Matches

2022-01-01 · CVPR 2022 1 · Jin-Man Park, Ue-Hwan Kim, Seon-Hoon Lee, Jong-Hwan Kim

Accurate change detection enables a wide range of tasks in visual surveillance, anomaly detection and mobile robotics. However, contemporary change detection approaches assume an ideal matching between the current and stored scenes, whereas only coarse matching is possible in real-world scenarios. Thus, contemporary approaches fail to show the reported performance in real-world settings. To overcome this limitation, we propose SimSaC. SimSaC concurrently conducts scene flow estimation and change detection and is able to detect changes with imperfect matches. To train SimSaC without additional manual labeling, we propose a training scheme with random geometric transformations and the cut-paste method. Moreover, we design an evaluation protocol which reflects performance in real-world settings. In designing the protocol, we collect a test benchmark dataset, which we claim as another contribution. Our comprehensive experiments verify that SimSaC displays robust performance even given imperfect matches and the performance margin compared to contemporary approaches is huge.

📄 PDF Abstract BibTeX

Code (1)

sammica/simsac 공식 구현 pytorch

Tasks

Anomaly DetectionChange DetectionScene Flow Estimation

Similar Papers 제목 키워드 기반

Correspondence Distillation from NeRF-based GAN

2022-12-19 · Yushi Lan, Chen Change Loy, Bo Dai

The neural radiance field (NeRF) has shown promising results in preserving the fine details of objects and scenes. However, unlike mesh-based representations, it remains an open problem to build dense correspondences acr…

NeRF

S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching

2020-04-03 · Hugo Germain, Guillaume Bourmaud, Vincent Lepetit

Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust corresp…

Visual Localization

S2DNet: Learning Image Features for Accurate Sparse-to-Dense Matching

2020-08-01 · ECCV 2020 8 · Hugo Germain, Guillaume Bourmaud, Vincent Lepetit

Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust corresp…

Visual Localization

PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence

2018-07-09 · ECCV 2018 9 · Sangryul Jeon, Seungryong Kim, Dongbo Min, Kwanghoon Sohn

This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images. To deal with intra…

regressionSemantic correspondence

Dual-Resolution Correspondence Networks

2020-06-16 · NeurIPS 2020 12 · Xinghui Li, Kai Han, Shuda Li, Victor Adrian Prisacariu

We tackle the problem of establishing dense pixel-wise correspondences between a pair of images. In this work, we introduce Dual-Resolution Correspondence Networks (DualRC-Net), to obtain pixel-wise correspondences in a …