Pablo Garrido

Pablo Garrido

Auto-generated profile, based on publicly available information

Pablo Garrido

Flawless AI, Los Angeles, United States of America

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
19 November 2024 in ACM Transactions on Graphics
Verified
Journal Article
Open access
KTKartik Teotia
Kartik Teotia
HKHyeongwoo Kim
Hyeongwoo Kim
PGPablo Garrido
Pablo Garrido
MHMarc Habermann
Marc Habermann
MEMohamed Elgharib
Mohamed Elgharib
CTChristian Theobalt
Christian Theobalt
Real-time rendering of human head avatars is a cornerstone of many computer graphics applications, such as augmented reality, video games, and films, to name a few. Recent approaches address this challenge with computationally efficient geometry primitives in a carefully calibrated multi-view setup. Albeit producing photorealistic head renderings, they often fail to represent complex motion changes, such as the mouth interior and strongly varying head poses. We propose a new method to generate highly dynamic and deformable human head avatars from multi-view imagery in real time. At the core of our method is a hierarchical representation of head models that can capture the complex dynamics of facial expressions and head movements. First, with rich facial features extracted from raw input frames, we learn to deform the coarse facial geometry of the template mesh. We then initialize 3D Gaussians on the deformed surface and refine their positions in a fine step. We train this coarse-to-fine facial avatar model along with the head pose as learnable parameters in an end-to-end framework. This enables not only controllable facial animation via video inputs but also high-fidelity novel view synthesis of challenging facial expressions, such as tongue deformations and fine-grained teeth structure under large motion changes. Moreover, it encourages the learned head avatar to generalize towards new facial expressions and head poses at inference time. We demonstrate the performance of our method with comparisons against the related methods on different datasets, spanning challenging facial expression sequences across multiple identities. We also show the potential application of our approach by demonstrating a cross-identity facial performance transfer application. We make the code available on our project page.

9 April 2024 in ACM Transactions on Graphics
Verified
Journal Article
Open access
KTKartik Teotia
Kartik Teotia
MRMallikarjun B R
Mallikarjun B R
XPXingang Pan
Xingang Pan
HKHyeongwoo Kim
Hyeongwoo Kim
PGPablo Garrido
Pablo Garrido
CTChristian Theobalt
Christian Theobalt
Multi-view volumetric rendering techniques have recently shown great potential in modeling and synthesizing high-quality head avatars. A common approach to capture full head dynamic performances is to track the underlying geometry using a mesh-based template or 3D cube-based graphics primitives. While these model-based approaches achieve promising results, they often fail to learn complex geometric details such as the mouth interior, hair, and topological changes over time. This article presents a novel approach to building highly photorealistic digital head avatars. Our method learns a canonical space via an implicit function parameterized by a neural network. It leverages multiresolution hash encoding in the learned feature space, allowing for high quality, faster training, and high-resolution rendering. At test time, our method is driven by a monocular RGB video. Here, an image encoder extracts face-specific features that also condition the learnable canonical space. This encourages deformation-dependent texture variations during training. We also propose a novel optical flow-based loss that ensures correspondences in the learned canonical space, thus encouraging artifact-free and temporally consistent renderings. We show results on challenging facial expressions and show free-viewpoint renderings at interactive real-time rates for a resolution of 480 x 270. Our method outperforms related approaches both visually and numerically. We will release our multiple-identity dataset to encourage further research.

27 October 2025
Verified
Conference Paper
Open access
PLPinxin Liu
Pinxin Liu
PZPengfei Zhang
Pengfei Zhang
HKHyeongwoo Kim
Hyeongwoo Kim
PGPablo Garrido
Pablo Garrido
ASAri Shapiro
Ari Shapiro
KOKyle Olszewski
Kyle Olszewski


13 August 2025 in arXiv
Verified
Preprint
Open access
PDF file
EEEray Eren
Eray Eren
QLQingju Liu
Qingju Liu
HKHyeongwoo Kim
Hyeongwoo Kim
PGPablo Garrido
Pablo Garrido
AAAbeer Alwan
Abeer Alwan
Prosody conveys rich emotional and semantic information of the speech signal as well as individual idiosyncrasies. We propose a stand-alone model that maps text-to-prosodic features such as F0 and energy and can be used in downstream tasks such as TTS. The ProMode encoder takes as input acoustic features and time-aligned textual content, both are partially masked, and obtains a fixed-length latent prosodic embedding. The decoder predicts acoustics in the masked region using both the encoded prosody input and unmasked textual content. Trained on the GigaSpeech dataset, we compare our method with state-of-the-art style encoders. For F0 and energy predictions, we show consistent improvements for our model at different levels of granularity. We also integrate these predicted prosodic features into a TTS system and conduct perceptual tests, which show higher prosody preference compared to the baselines, demonstrating the model's potential in tasks where prosody modeling is important.