SuP: Sub-cloud Driven Point Cloud Registration
SuP turns low-overlap point cloud registration into high-overlap sub-cloud anchor mining, using DSAM, OPS, MPN, and merge-to-match to recover reliable correspondences from ambiguous partial scans.
Jan 1, 2026
Self-calibrating structured light three-dimensional imaging method with fringe projection
A self-calibrating structured-light 3D imaging method that uses fringe projection to reduce manual calibration burden in 3D reconstruction.
Jan 1, 2026
Learning-based reconstruction of moving transparent objects
A learning-based 3D reconstruction method for moving transparent objects, targeting the difficult case where refraction and motion break standard structured-light assumptions.
Jan 1, 2026
Volume Measurement Technology of Dispensing Transparent Adhesives Based on Line Laser Scanning
Conference version of the transparent-adhesive volume-measurement work, using line-laser scanning for dispensing inspection.
Jan 1, 2025
SFRF6D: Selective Fewer-Reference Fusion for 6D Pose Estimation
SFRF6D is a model-free 6D pose estimation framework that uses only a few RGB-D reference images, combining reference-view rendering, geometry-guided sparse attention, and coarse-to-fine pose selection for robust estimation under occlusion.
Jan 1, 2025
Photometric stereo-based defect detection for lithium battery top covers
Detecting surface defects on lithium battery top covers is critical for ensuring their performance, reliability, and longevity.
Jan 1, 2025
GCMA6D: Graph Convolution and Cross-Modality Attention Fusion for 6D Pose Estimation
GCMA6D is an RGB-D 6D pose estimation network that combines 3D graph convolution, Large Kernel Attention, and cross-modality attention fusion to improve robustness for occluded and low-texture objects.
Jan 1, 2025
FPD: Fringe Photometric Deflectometry when Fringe Meets Photometric Stereo
FPD fuses Phase Measuring Deflectometry and Photometric Stereo with per-pixel reflectance-aware weights, using PMD in specular regions and PS in diffuse/detail-rich regions for robust 3D reconstruction and defect detection.
Jan 1, 2025
A Reversible Grayscale Method Based on Bit-Field Multi-Channel Fusion Encoding
A grayscale-compatible color encoding method that packs standard 8-bit grayscale into the high bits of a 16-bit image and stores compact hue/saturation hints in the low bits, enabling color restoration while preserving normal grayscale viewing.
Jan 1, 2025
SemReg: Semantics-Constrained Point Cloud Registration
SemReg incorporates semantic labels as geometric registration constraints, enabling robust point cloud alignment even in textureless or symmetry-ambiguous regions where purely geometric methods fail, with state-of-the-art results on indoor and outdoor benchmarks.
Sep 1, 2024