Hpointloc: Point-based Indoor Place Recognition Using Synthetic RGB-D Images

Abstract

We present a novel dataset named as HPointLoc, specially designed for exploring capabilities of visual place recognition in indoor environment and loop detection in simultaneous localization and mapping. The loop detection sub-task is especially relevant when a robot with an on-board RGB-D camera can drive past the same place (``Point") at different angles. The dataset is based on the popular Habitat simulator, in which it is possible to generate photorealistic indoor scenes using both own sensor data and open datasets, such as Matterport3D. To study the main stages of solving the place recognition problem on the HPointLoc dataset, we proposed a new modular approach named as PNTR. It first performs an image retrieval with the Patch-NetVLAD method, then extracts keypoints and matches them using R2D2, LoFTR or SuperPoint with SuperGlue, and finally performs a camera pose optimization step with TEASER++. Such a solution to the place recognition problem has not been previously studied in e

Stats

• citations9
• S2 citations—
• github stars37
• HF likes0
• heat score10.66
• arxiv keyyudin2022hpointloc

Related papers

• Pointnetvlad: Deep Point Cloud Based Retrieval For Large-scale Place Recognition (2018)25.45
• Crossloc3d: Aerial-ground Cross-source 3D Place Recognition (2023)9.23
• Lpd-net: 3D Point Cloud Learning For Large-scale Place Recognition And Environment Analysis (2018)18.40
• LCD -- Line Clustering And Description For Place Recognition (2020)8.60
• CSCPR: Cross-source-context Indoor RGB-D Place Recognition (2024)0.00
• Logg3d-net: Locally Guided Global Descriptor Learning For 3D Place Recognition (2021)19.02
• Eigenplaces: Training Viewpoint Robust Models For Visual Place Recognition (2023)15.46
• Sparse-to-dense Hypercolumn Matching For Long-term Visual Localization (2019)12.99