Luvision resource
Computational imaging
  • CrossNet++: Cross-Scale Large-Parallax Warping for Reference-Based Super-Resolution
  • DeepCAD: Deep self-supervised learning for calcium imaging denoising
Large-scale Reconstruction
  • Multiview Stereo
    • SurRF: Unsupervised Multi-view Stereopsis by Learning Surface Radiance Field
    • SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis
    • SurfaceNet+: An End-to-end 3D Neural Network for Very Sparse Multi-View Stereopsis
  • RGBD Reconstruction
    • OccuSeg: Occupancy-aware 3D Instance Segmentation
    • Real-Time Globally Consistent Dense 3D Reconstruction With Online Texturing
    • BuildingFusion: Semantic-aware Structural Building-scale 3D Reconstruction
    • FlashFusion: An efficient dense 3D reconstruction that only relies on CPU computing.
    • iDFusion: Globally Consistent Dense 3D Reconstruction from RGB-D and Inertial Measurements.
    • INS-Conv: Incremental Sparse Convolution for Online 3D segmentation
    • MILD: Multi-Index hashing for Loop closure Detection
Datasets and benchmark
  • GigaMVS: A Benchmark for Ultra-large-scale Gigapixel-level 3D Reconstruction
  • PANDA: A Gigapixel-level Human-centric Video Dataset
Luvision resource
  • Datasets_and_benchmark
  • README.md

Datasets and benchmark

  • GigaMVS: A Benchmark for Ultra-large-scale Gigapixel-level 3D Reconstruction
  • PANDA: A Gigapixel-level Human-centric Video Dataset
Next

2022, luvision Revision ca0fbf4
Built with GitHub Pages using a theme provided by RunDocs.
Luvision resource
main
GitHub
Homepage
Issues
Download

This Software is under the terms of MIT License.