Combining Neural Fields and Deformation Models for Non-Rigid 3D Motion Reconstruction from Partial Data

We introduce a novel, data-driven approach for reconstructing temporally coherent 3D motion from unstructured and potentially partial observations of non-rigidly deforming shapes. Our goal is to achieve high-fidelity motion reconstructions for shapes that undergo near-isometric deformations, such as humans wearing loose clothing. The key novelty of our work lies in its ability to combine implicit shape representations with explicit mesh-based deformation models, enabling detailed and temporally coherent motion reconstructions without relying on parametric shape models or decoupling shape and motion. Each frame is represented as a neural field decoded from a feature space where observations over time are fused, hence preserving geometric details present in the input data. Temporal coherence is enforced with a near-isometric deformation constraint between adjacent frames that applies to the underlying surface in the neural field. Our method outperforms state-of-the-art approaches, as demonstrated by its application to human and animal motion sequences reconstructed from monocular depth videos.

Deformation-Guided Unsupervised Non-Rigid Shape Matching

We present an unsupervised data-driven approach for non-rigid shape matching. Shape matching identifies correspondences between two shapes and is a fundamental step in many computer vision and graphics applications. Our approach is designed to be particularly robust when matching shapes digitized using 3D scanners that contain fine geometric detail and suffer from different types of noise including topological noise caused by the coalescence of spatially close surface regions. We build on two strategies. First, using a hierarchical patch based shape representation we match shapes consistently in a coarse to fine manner, allowing for robustness to noise. This multi-scale representation drastically reduces the dimensionality of the problem when matching at the coarsest scale, rendering unsupervised learning feasible. Second, we constrain this hierarchical matching to be reflected in 3D by fitting a patch-wise near-rigid deformation model. Using this constraint, we leverage spatial continuity at different scales to capture global shape properties, resulting in matchings that generalize well to data with different deformations and noise characteristics. Experiments demonstrate that our approach obtains significantly better results on raw 3D scans than state-of-the-art methods, while performing on-par on standard test scenarios.

4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements

This work presents 4DHumanOutfit, a new dataset of densely sampled spatio-temporal 4D human motion data of different actors, outfits and motions. The dataset is designed to contain different actors wearing different outfits while performing different motions in each outfit. In this way, the dataset can be seen as a cube of data containing 4D motion sequences along 3 axes with identity, outfit and motion. This rich dataset has numerous potential applications for the processing and creation of digital humans, e.g. augmented reality, avatar creation and virtual try on. 4DHumanOutfit is released for research purposes at https://kinovis.inria.fr/4dhumanoutfit/. In addition to image data and 4D reconstructions, the dataset includes reference solutions for each axis. We present independent baselines along each axis that demonstrate the value of these reference solutions for evaluation tasks.

Correspondence-free online human motion retargeting

We present a novel data-driven framework for unsupervised human motion retargeting which animates a target body shape with a source motion. This allows to retarget motions between different characters by animating a target subject with a motion of a source subject. Our method is correspondence-free,~\ie neither spatial correspondences between the source and target shapes nor temporal correspondences between different frames of the source motion are required. Our proposed method directly animates a target shape with arbitrary sequences of humans in motion, possibly captured using 4D acquisition platforms or consumer devices. Our framework takes into account long-term temporal context of $1$ second during retargeting while accounting for surface details. To achieve this, we take inspiration from two lines of existing work: skeletal motion retargeting, which leverages long-term temporal context at the cost of surface detail, and surface-based retargeting, which preserves surface details without considering long-term temporal context. We unify the advantages of these works by combining a learnt skinning field with a skeletal retargeting approach. During inference, our method runs online,~\ie the input can be processed in a serial way, and retargeting is performed in a single forward pass per frame. Experiments show that including long-term temporal context during training improves the method's accuracy both in terms of the retargeted skeletal motion and the detail preservation. Furthermore, our method generalizes well on unobserved motions and body shapes. We demonstrate that the proposed framework achieves state-of-the-art results on two test datasets.

Spatio-temporal motion completion using a sequence of latent primitives

We propose a markerless performance capture method that computes a temporally coherent 4D representation of an actor deforming over time from a sparsely sampled sequence of untracked 3D point clouds. Our method proceeds by latent optimization with a spatio-temporal motion prior. Recently, task generic motion priors have been introduced and propose a coherent representation of human motion based on a single latent code, with encouraging results with short sequences and given temporal correspondences. Extending these methods to longer sequences without correspondences is all but straightforward. One latent code proves inefficient to encode longer term variability, and latent space optimization will be very susceptible to erroneous local minima due to possible inverted pose fittings. We address both problems by learning a motion prior that encodes a 4D human motion sequence into a sequence of latent primitives instead of one latent code. We also propose an additional mapping encoder which directly projects a sequence of point clouds into the learned latent space to provide a good initialization of the latent representation at inference time. Our temporal decoding from latent space is implicit and continuous in time, providing flexibility with temporal resolution. We show experimentally that our method outperforms state-of-the-art motion priors.

Neural Human Deformation Transfer

We consider the problem of human deformation transfer, where the goal is to retarget poses between different characters. Traditional methods that tackle this problem require a clear definition of the pose, and use this definition to transfer poses between characters. In this work, we take a different approach and transform the identity of a character into a new identity without modifying the character's pose. This offers the advantage of not having to define equivalences between 3D human poses, which is not straightforward as poses tend to change depending on the identity of the character performing them, and as their meaning is highly contextual. To achieve the deformation transfer, we propose a neural encoder-decoder architecture where only identity information is encoded and where the decoder is conditioned on the pose. We use pose independent representations, such as isometry-invariant shape characteristics, to represent identity features. Our model uses these features to supervise the prediction of offsets from the deformed pose to the result of the transfer. We show experimentally that our method outperforms state-of-the-art methods both quantitatively and qualitatively, and generalises better to poses not seen during training. We also introduce a fine-tuning step that allows to obtain competitive results for extreme identities, and allows to transfer simple clothing.

Learning Implicit 3D Representations of Dressed Humans from Sparse Views

Recently, data-driven single-view reconstruction methods have shown great progress in modeling 3D dressed humans. However, such methods suffer heavily from depth ambiguities and occlusions inherent to single view inputs. In this paper, we address such issues by lifting the single-view input with additional views and investigate the best strategy to suitably exploit information from multiple views. We propose an end-to-end approach that learns an implicit 3D representation of dressed humans from sparse camera views. Specifically, we introduce two key components: first an attention-based fusion layer that learns to aggregate visual information from several viewpoints; second a mechanism that encodes local 3D patterns under the multi-view context. In the experiments, we show the proposed approach outperforms the state of the art on standard data both quantitatively and qualitatively. Additionally, we apply our method on real data acquired with a multi-camera platform and demonstrate our approach can obtain results comparable to multi-view stereo with dramatically less views.

3D Morphable Face Models -- Past, Present and Future

In this paper, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed. The challenges in building and applying these models, namely capture, modeling, image formation, and image analysis, are still active research topics, and we review the state-of-the-art in each of these areas. We also look ahead, identifying unsolved challenges, proposing directions for future research and highlighting the broad range of current and future applications.

A Decoupled 3D Facial Shape Model by Adversarial Training

Data-driven generative 3D face models are used to compactly encode facial shape data into meaningful parametric representations. A desirable property of these models is their ability to effectively decouple natural sources of variation, in particular identity and expression. While factorized representations have been proposed for that purpose, they are still limited in the variability they can capture and may present modeling artifacts when applied to tasks such as expression transfer. In this work, we explore a new direction with Generative Adversarial Networks and show that they contribute to better face modeling performances, especially in decoupling natural factors, while also achieving more diverse samples. To train the model we introduce a novel architecture that combines a 3D generator with a 2D discriminator that leverages conventional CNNs, where the two components are bridged by a geometry mapping layer. We further present a training scheme, based on auxiliary classifiers, to explicitly disentangle identity and expression attributes. Through quantitative and qualitative results on standard face datasets, we illustrate the benefits of our model and demonstrate that it outperforms competing state of the art methods in terms of decoupling and diversity.

A Multilinear Tongue Model Derived from Speech Related MRI Data of the Human Vocal Tract

We present a multilinear statistical model of the human tongue that captures anatomical and tongue pose related shape variations separately. The model is derived from 3D magnetic resonance imaging data of 11 speakers sustaining speech related vocal tract configurations. The extraction is performed by using a minimally supervised method that uses as basis an image segmentation approach and a template fitting technique. Furthermore, it uses image denoising to deal with possibly corrupt data, palate surface information reconstruction to handle palatal tongue contacts, and a bootstrap strategy to refine the obtained shapes. Our evaluation concludes that limiting the degrees of freedom for the anatomical and speech related variations to 5 and 4, respectively, produces a model that can reliably register unknown data while avoiding overfitting effects. Furthermore, we show that it can be used to generate a plausible tongue animation by tracking sparse motion capture data.