2. Superpixels RevisitedLibrary containing 7 state-of-the-art superpixel algorithms with a total of 9 implementations used for evaluation purposes in [1] utilizing an extended version of the Berkeley Segmentation Benchmark.
3. Mesh VoxelizationC++ implementation for computing occupancy grids and signed distance functions (SDFs) from watertight meshes.
5. Caffe ToolsSome tools and examples for pyCaffe including LMDB I/O, custom Python layers and monitoring training error and loss.
7. Graph Based Image SegmentationImplementation of efficient graph-based image segmentation as proposed by Felzenswalb and Huttenlocher [1] that can be used to generate oversegmentations.
8. Mesh EvaluationEfficient C++ implementation of mesh-to-mesh and mesh-to-point distance.
10. Superpixel BenchmarkAn extensive evaluation and comparison of 28 state-of-the-art superpixel algorithms on 5 datasets.
14. daml-shape-completionCVPR'18 implementation of (deterministic) amortized maximum likelihood (AML) for weakly-supervised shape completion.
16. mesh-fusionPython tool for obtaining watertight meshes using TSDF fusion.
17. flow-io-opencvFork and OpenCV wrapper of the optical flow I/O and visualization code provided as part of the Sintel dataset [1].