Thiemo Alldieck

Thiemo Alldieck

Auto-generated profile, based on publicly available information

Thiemo Alldieck

Google research

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 October 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
DTDenis Tome
Denis Tome
TAThiemo Alldieck
Thiemo Alldieck
PPPatrick Peluse
Patrick Peluse
GPGerard Pons-Moll
Gerard Pons-Moll
LALourdes Agapito
Lourdes Agapito
FTFernando de la Torre
Fernando de la Torre
We present a new solution to egocentric 3D body pose estimation from monocular images captured from a downward looking fish-eye camera installed on the rim of a head mounted virtual reality device. This unusual viewpoint leads to images with unique visual appearance, characterized by severe self-occlusions and strong perspective distortions that result in a drastic difference in resolution between lower and upper body. We propose a new encoder-decoder architecture with a novel multi-branch decoder designed specifically to account for the varying uncertainty in 2D joint locations. Our quantitative evaluation, both on synthetic and real-world datasets, shows that our strategy leads to substantial improvements in accuracy over state of the art egocentric pose estimation approaches. To tackle the severe lack of labelled training data for egocentric 3D pose estimation we also introduced a large-scale photo-realistic synthetic dataset. $\boldsymbol{x}$ R-EgoPose offers 383K frames of high quality renderings of people with diverse skin tones, body shapes and clothing, in a variety of backgrounds and lighting conditions, performing a range of actions. Our experiments show that the high variability in our new synthetic training corpus leads to good generalization to real world footage and to state of the art results on real world datasets with ground truth. Moreover, an evaluation on the Human3.6M benchmark shows that the performance of our method is on par with top performing approaches on the more classic problem of 3D human pose from a third person viewpoint.

15 August 2017
Verified
Book Chapter
Closed access
PDF file
TAThiemo Alldieck
Thiemo Alldieck
MKMarc Kassubeck
Marc Kassubeck
BWBastian Wandt
Bastian Wandt
BRBodo Rosenhahn
Bodo Rosenhahn
MMMarcus Magnor
Marcus Magnor

21 November 2024
Verified
Book Chapter
Closed access
PDF file
NKNikos Kolotouros
Nikos Kolotouros
TAThiemo Alldieck
Thiemo Alldieck
ECEnric Corona
Enric Corona
EBEduard Gabriel Bazavan
Eduard Gabriel Bazavan
CSCristian Sminchisescu
Cristian Sminchisescu

21 November 2024
Verified
Book Chapter
Closed access
PDF file
TAThiemo Alldieck
Thiemo Alldieck
NKNikos Kolotouros
Nikos Kolotouros
CSCristian Sminchisescu
Cristian Sminchisescu

31 March 2020 in arXiv
Verified
Preprint
Open access
PDF file
AMAymen Mir
Aymen Mir
TAThiemo Alldieck
Thiemo Alldieck
GPGerard Pons-Moll
Gerard Pons-Moll
In this paper, we present a simple yet effective method to automatically transfer textures of clothing images (front and back) to 3D garments worn on top SMPL, in real time. We first automatically compute training pairs of images with aligned 3D garments using a custom non-rigid 3D to 2D registration method, which is accurate but slow. Using these pairs, we learn a mapping from pixels to the 3D garment surface. Our idea is to learn dense correspondences from garment image silhouettes to a 2D-UV map of a 3D garment surface using shape information alone, completely ignoring texture, which allows us to generalize to the wide range of web images. Several experiments demonstrate that our model is more accurate than widely used baselines such as thin-plate-spline warping and image-to-image translation networks while being orders of magnitude faster. Our model opens the door for applications such as virtual try-on, and allows for generation of 3D humans with varied textures which is necessary for learning.

15 June 2023 in arXiv
Verified
Preprint
Open access
PDF file
NKNikos Kolotouros
Nikos Kolotouros
TAThiemo Alldieck
Thiemo Alldieck
AZAndrei Zanfir
Andrei Zanfir
EBEduard Gabriel Bazavan
Eduard Gabriel Bazavan
MFMihai Fieraru
Mihai Fieraru
CSCristian Sminchisescu
Cristian Sminchisescu
We present DreamHuman, a method to generate realistic animatable 3D human avatar models solely from textual descriptions. Recent text-to-3D methods have made considerable strides in generation, but are still lacking in important aspects. Control and often spatial resolution remain limited, existing methods produce fixed rather than animated 3D human models, and anthropometric consistency for complex structures like people remains a challenge. DreamHuman connects large text-to-image synthesis models, neural radiance fields, and statistical human body models in a novel modeling and optimization framework. This makes it possible to generate dynamic 3D human avatars with high-quality textures and learned, instance-specific, surface deformations. We demonstrate that our method is capable to generate a wide variety of animatable, realistic 3D human models from text. Our 3D models have diverse appearance, clothing, skin tones and body shapes, and significantly outperform both generic text-to-3D approaches and previous text-based 3D avatar generators in visual fidelity. For more results and animations please check our website at https://dream-human.github.io.