Self Supervised Human Depth Estimation From Monocular Videos

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=b_YTf4FwYA8


Duration: 1:01
1,195 views
11

Learn all the ways Microsoft is a part of CVPR 2020: https://www.microsoft.com/en-us/research/event/cvpr-2020/



Other Videos By Microsoft Research


2020-06-14Relation aware Global Attention for Person Re identification
2020-06-14TextureFusion: High-Quality Texture Acquisition for Real-Time RGB-D Scanning
2020-06-14ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture
2020-06-14Disentangled and Controllable Face Image Generation via 3D Imitative Contrastive Learning
2020-06-14HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
2020-06-14Advancing High Fidelity Identity Swapping for Forgery Detection
2020-06-14DIST: Rendering Deep Implicit Signed Distance Function With Differentiable Sphere Tracing
2020-06-14Why Having 10,000 Parameters in Your Camera Model Is Better Than Twelve
2020-06-14Combining Human and Machine Intelligence to Describe Images to People with Visual Impairments
2020-06-14Geometry Aware Satellite to Ground Image Synthesis for Urban Areas
2020-06-14Self Supervised Human Depth Estimation From Monocular Videos
2020-06-14LSM: Learning Subspace Minimization for Low-level Vision
2020-06-14MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
2020-06-14MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation
2020-06-14Leveraging Photometric Consistency over Time for Sparsely Supervised Hand Object Reconstruction
2020-06-14Deep Shutter Unrolling Network
2020-06-14Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re W
2020-06-14MMTM: Multimodal Transfer Module for CNN Fusion
2020-06-14Learning Texture Transformer Network for Image Super Resolution
2020-06-14BachGAN: High-Resolution Image Synthesis from Salient Object Layout
2020-06-14Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training