no code implementations • 25 Mar 2024 • Laiyan Ding, Panwen Hu, Jie Li, Rui Huang
To address this RGB-TSDF distribution difference, we propose a two-stage network with a 3D RGB feature completion module that completes RGB features with meaningful values for occluded areas.
1 code implementation • 12 Oct 2021 • Hualie Jiang, Laiyan Ding, Junjie Hu, Rui Huang
Unsupervised learning of depth from indoor monocular videos is challenging as the artificial environment contains many textureless regions.
1 code implementation • 30 Aug 2021 • Hualie Jiang, Laiyan Ding, Zhenglong Sun, Rui Huang
We first propose an outlier masking technique that considers the occluded or dynamic pixels as statistical outliers in the photometric error map.
no code implementations • 29 Jun 2021 • Jie Li, Laiyan Ding, Rui Huang
3D semantic scene completion and 2D semantic segmentation are two tightly correlated tasks that are both essential for indoor scene understanding, because they predict the same semantic classes, using positively correlated high-level features.
1 code implementation • 3 Mar 2020 • Hualie Jiang, Laiyan Ding, Zhenglong Sun, Rui Huang
Unsupervised learning of depth and ego-motion from unlabelled monocular videos has recently drawn great attention, which avoids the use of expensive ground truth in the supervised one.
Ranked #53 on Monocular Depth Estimation on KITTI Eigen split