Face2Face: Real-Time Face Capture and Reenactment of RGB Videos
- Justus Thies, M. Zollhöfer, M. Stamminger, C. Theobalt, M. Nießner
- Computer ScienceComputer Vision and Pattern Recognition
- 27 June 2016
A novel approach for real-time facial reenactment of a monocular target video sequence (e.g., Youtube video) that addresses the under-constrained problem of facial identity recovery from monocular video by non-rigid model-based bundling and re-render the manipulated output video in a photo-realistic fashion.
Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision
- Dushyant Mehta, Helge Rhodin, C. Theobalt
- Computer ScienceInternational Conference on 3D Vision
- 29 November 2016
We propose a CNN-based approach for 3D human body pose estimation from single RGB images that addresses the issue of limited generalizability of models trained solely on the starkly limited publicly…
VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
- Dushyant Mehta, Srinath Sridhar, C. Theobalt
- Computer ScienceACM Transactions on Graphics
- 3 May 2017
This work presents the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera and shows that the approach is more broadly applicable than RGB-D solutions, i.e., it works for outdoor scenes, community videos, and low quality commodity RGB cameras.
BundleFusion: real-time globally consistent 3D reconstruction using on-the-fly surface re-integration
- Angela Dai, M. Nießner, M. Zollhöfer, S. Izadi, C. Theobalt
- Computer ScienceTOGS
- 5 April 2016
This work systematically addresses issues with a novel, real-time, end-to-end reconstruction framework, which outperforms state-of-the-art online systems with quality on par to offline methods, but with unprecedented speed and scan completeness.
GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB
- Franziska Mueller, Florian Bernard, C. Theobalt
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 4 December 2017
This work proposes a novel approach for the synthetic generation of training data that is based on a geometrically consistent image-to-image translation network, and uses a neural network that translates synthetic images to "real" images, such that the so-generated images follow the same statistical distribution as real-world hand images.
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
- Peng Wang, Lingjie Liu, Yuan Liu, C. Theobalt, T. Komura, Wenping Wang
- Computer ScienceNeural Information Processing Systems
- 20 June 2021
Experiments show that NeuS outperforms the state-of-the-arts in high-quality surface reconstruction, especially for objects and scenes with complex structures and self-occlusion.
MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction
- Ayush Tewari, M. Zollhöfer, C. Theobalt
- Computer ScienceIEEE International Conference on Computer Vision…
- 30 March 2017
A novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image and can be trained end-to-end in an unsupervised manner, which renders training on very large real world data feasible.
Single-Shot Multi-person 3D Pose Estimation from Monocular RGB
- Dushyant Mehta, Oleksandr Sotnychenko, C. Theobalt
- Computer ScienceInternational Conference on 3D Vision
- 9 December 2017
We propose a new single-shot method for multi-person 3D pose estimation in general scenes from a monocular RGB camera. Our approach uses novel occlusion-robust pose-maps (ORPM) which enable full body…
Neural Sparse Voxel Fields
- Lingjie Liu, Jiatao Gu, Kyaw Zaw Lin, Tat-Seng Chua, C. Theobalt
- Computer ScienceNeural Information Processing Systems
- 22 July 2020
This work introduces Neural Sparse Voxel Fields (NSVF), a new neural scene representation for fast and high-quality free-viewpoint rendering that is over 10 times faster than the state-of-the-art (namely, NeRF) at inference time while achieving higher quality results.
StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis
- Jiatao Gu, Lingjie Liu, Peng Wang, C. Theobalt
- Computer ScienceInternational Conference on Learning…
- 18 October 2021
StyleNeRF is a 3D-aware generative model for photo-realistic high-resolution image synthesis with high multi-view consistency and enables control of camera poses and different levels of styles, which can generalize to unseen views and supports challenging tasks, including style mixing and semantic editing.
...
...