A Deeper Look into DeepCap

11/20/2021
by   Marc Habermann, et al.
10

Human performance capture is a highly important computer vision problem with many applications in movie production and virtual/augmented reality. Many previous performance capture approaches either required expensive multi-view setups or did not recover dense space-time coherent geometry with frame-to-frame correspondences. We propose a novel deep learning approach for monocular dense human performance capture. Our method is trained in a weakly supervised manner based on multi-view supervision completely removing the need for training data with 3D ground truth annotations. The network architecture is based on two separate networks that disentangle the task into a pose estimation and a non-rigid surface deformation step. Extensive qualitative and quantitative evaluations show that our approach outperforms the state of the art in terms of quality and robustness. This work is an extended version of DeepCap where we provide more detailed explanations, comparisons and results as well as applications.

READ FULL TEXT

page 1

page 4

page 8

page 9

page 10

page 11

page 14

research
03/18/2020

DeepCap: Monocular Human Performance Capture Using Weak Supervision

Human performance capture is a highly important computer vision problem ...
research
11/25/2020

Deep Physics-aware Inference of Cloth Deformation for Monocular Human Performance Capture

Recent monocular human performance capture approaches have shown compell...
research
08/07/2017

MonoPerfCap: Human Performance Capture from Monocular Video

We present the first marker-less approach for temporally coherent 3D per...
research
05/25/2023

EgoHumans: An Egocentric 3D Multi-Human Benchmark

We present EgoHumans, a new multi-view multi-human video benchmark to ad...
research
05/04/2021

Real-time Deep Dynamic Characters

We propose a deep videorealistic 3D human character model displaying hig...
research
05/04/2021

Weak Multi-View Supervision for Surface Mapping Estimation

We propose a weakly-supervised multi-view learning approach to learn cat...
research
09/19/2022

NeuralMarker: A Framework for Learning General Marker Correspondence

We tackle the problem of estimating correspondences from a general marke...

Please sign up or login with your details

Forgot password? Click here to reset