Search Results for author:
Found 13 papers, 4 papers with code
BEV2PR: BEV-Enhanced Visual Place Recognition with Structural Cues
To tackle the above issues, we design a new BEV-enhanced VPR framework, nemely BEV2PR, which can generate a composite descriptor with both visual cues and spatial awareness solely based on a single camera.
Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes
However, common distance field based implicit representations, specifically signed distance field (SDF) for watertight shapes or unsigned distance field (UDF) for arbitrary shapes, routinely suffer from degradation of reconstruction accuracy when converting to explicit surface points and meshes.
Fast and Interpretable 2D Homography Decomposition: Similarity-Kernel-Similarity and Affine-Core-Affine Transformations
Under the minimal $4$-point configuration, the first and the last similarity transformations in SKS are computed by two anchor points on target and source planes, respectively.
Incremental Rotation Averaging Revisited and More: A New Rotation Averaging Benchmark
In addition, to further address the limitations of the existing rotation averaging benchmark of relying on the slightly outdated Bundler camera calibration results as ground truths and focusing solely on rotation estimation accuracy, this paper presents a new COLMAP-based rotation averaging benchmark that incorporates a cross check between COLMAP and Bundler, and employ the accuracy of both rotation and downstream location estimation as evaluation metrics, which is desired to provide a more reliable and comprehensive evaluation tool for the rotation averaging research.
Shape Anchor Guided Holistic Indoor Scene Understanding
This paper proposes a shape anchor guided learning strategy (AncLearn) for robust holistic indoor scene understanding.
Dense Semantic 3D Map Based Long-Term Visual Localization with Hybrid Features
Visual localization plays an important role in many applications.
Graph-Based Parallel Large Scale Structure from Motion
After local reconstructions, we construct a minimum spanning tree (MinST) to find accurate similarity transformations.
Complete Scene Reconstruction by Merging Images and Laser Scans
Experimental evaluations on two ancient Chinese architecture datasets demonstrate the effectiveness of our proposed complete scene reconstruction pipeline.
Visual Localization Using Sparse Semantic 3D Map
Accurate and robust visual localization under a wide range of viewing condition variations including season and illumination changes, as well as weather and day-night variations, is the key component for many computer vision and robotics applications.
Large Scale Urban Scene Modeling from MVS Meshes
There are two major steps in our framework: segmentation and building modeling.
CSfM: Community-based Structure from Motion
The global manner has the advantage of simultaneously estimating all camera poses, but it is usually sensitive to epipolar geometry outliers.
HSfM: Hybrid Structure-from-Motion
In this work, we propose a new hybrid SfM method to tackle the issues of efficiency, accuracy and robustness in a unified framework.
Dynamic Parallel and Distributed Graph Cuts
Through both the splitting and merging, we further propose a dynamic parallel and distributed graph-cuts algorithm with guaranteed convergence to the globally optimal solutions within a predefined number of iterations.
