Virtual point removal for large-scale 3D point clouds with multiple glass planes


Underwater image restoration using geodesic color distance and complete image formation model


Single image reflection removal using non-linearly synthesized glass images and semantic context


Glass reflection removal using co-saliency based image alignment and low-rank matrix completion in gradient domain

Stitching for multi-view videos with large parallax based on adaptive pixel warping


Saliency-based initialisation of Gaussian mixture models for fully-automatic object segmentation

Saliency detection for 3D surface geometry using semi-regular meshes

Saliency detection for panoramic landscape images of outdoor scenes


Video deraining and desnowing using temporal correlation and low-rank matrix completion

Spatiotemporal saliency detection for video sequences based on random walk with restart

FDQM: fast quality metric for depth maps without view synthesis

Large-scale 3D point cloud compression using adaptive radial distance prediction in hybrid coordinate domains


Bit allocation algorithm with novel view synthesis distortion model for multi-view video plus depth coding

Multiscale saliency detection using random walk with restart


Correspondence matching of multi-view video sequences using mutual information based similarity measure

Optimal binary encoding scheme for the fast motion estimation based on Hamming distances

Optimized contrast enhancement for real-time image and video dehazing

Consistent stereo matching under varying radiometric conditions


Time-of-flight sensor and color camera calibration for multi-view acquisition

Vision-based cleaning area control for cleaning robots

Reconstruction depth adaptive coding of digital holograms


Geometry contrast enhancement for 3D point models using histogram modification


Compression of 3-D point visual data using vector quantization and rate-distortion optimization


Lossless compression of 3-D point data in QSplat representation

Rate-distortion optimized compression and view-dependent transmission of 3-D normal meshes


An efficient 3D mesh compression technique based on triangle fan structure