About

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

Greatest papers with code

Atlas: End-to-End 3D Scene Reconstruction from Posed Images

ECCV 2020 magicleap/Atlas

Traditional approaches to 3D reconstruction rely on an intermediate representation of depth maps prior to estimating a full 3D model of a scene.

3D RECONSTRUCTION 3D SCENE RECONSTRUCTION 3D SEMANTIC SEGMENTATION

4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks

CVPR 2019 StanfordVL/MinkowskiEngine

To overcome challenges in the 4D space, we propose the hybrid kernel, a special case of the generalized sparse convolution, and the trilateral-stationary conditional random field that enforces spatio-temporal consistency in the 7D space-time-chroma space.

3D SEMANTIC SEGMENTATION 4 4D SPATIO TEMPORAL SEMANTIC SEGMENTATION

DeepGCNs: Can GCNs Go as Deep as CNNs?

ICCV 2019 lightaime/deep_gcns_torch

Finally, we use these new concepts to build a very deep 56-layer GCN, and show how it significantly boosts performance (+3. 7% mIoU over state-of-the-art) in the task of point cloud semantic segmentation.

3D SEMANTIC SEGMENTATION 4

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

CVPR 2018 loicland/superpoint_graph

We propose a novel deep learning-based framework to tackle the challenge of semantic segmentation of large-scale point clouds of millions of points.

 Ranked #1 on Semantic Segmentation on Semantic3D (oAcc metric)

3D SEMANTIC SEGMENTATION