ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D image

Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular approaches still struggle to recover fine geometric details such as face, hands or cloth wrinkles. They are also easily prone to depth ambiguities that result in distorted geometries along the camera optical axis. In this paper, we explore the benefits of incorporating depth observations in the reconstruction process by introducing ANIM, a novel method that reconstructs arbitrary 3D human shapes from single-view RGB-D images with an unprecedented level of accuracy. Our model learns geometric details from both multi-resolution pixel-aligned and voxel-aligned features to leverage depth information and enable spatial relationships, mitigating depth ambiguities. We further enhance the quality of the reconstructed shape by introducing a depth-supervision strategy, which improves the accuracy of the signed distance field estimation of points that lie on the reconstructed surface. Experiments demonstrate that ANIM outperforms state-of-the-art works that use RGB, surface normals, point cloud or RGB-D data as input. In addition, we introduce ANIM-Real, a new multi-modal dataset comprising high-quality scans paired with consumer-grade RGB-D camera, and our protocol to fine-tune ANIM, enabling high-quality reconstruction from real-world human capture.

HISR: Hybrid Implicit Surface Representation for Photorealistic 3D Human Reconstruction

Neural reconstruction and rendering strategies have demonstrated state-of-the-art performances due, in part, to their ability to preserve high level shape details. Existing approaches, however, either represent objects as implicit surface functions or neural volumes and still struggle to recover shapes with heterogeneous materials, in particular human skin, hair or clothes. To this aim, we present a new hybrid implicit surface representation to model human shapes. This representation is composed of two surface layers that represent opaque and translucent regions on the clothed human body. We segment different regions automatically using visual cues and learn to reconstruct two signed distance functions (SDFs). We perform surface-based rendering on opaque regions (e.g., body, face, clothes) to preserve high-fidelity surface normals and volume rendering on translucent regions (e.g., hair). Experiments demonstrate that our approach obtains state-of-the-art results on 3D human reconstructions, and also shows competitive performances on other objects.

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.

MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Vision

We present MedShapeNet, a large collection of anatomical shapes (e.g., bones, organs, vessels) and 3D surgical instrument models. Prior to the deep learning era, the broad application of statistical shape models (SSMs) in medical image analysis is evidence that shapes have been commonly used to describe medical data. Nowadays, however, state-of-the-art (SOTA) deep learning algorithms in medical imaging are predominantly voxel-based. In computer vision, on the contrary, shapes (including, voxel occupancy grids, meshes, point clouds and implicit surface models) are preferred data representations in 3D, as seen from the numerous shape-related publications in premier vision conferences, such as the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), as well as the increasing popularity of ShapeNet (about 51,300 models) and Princeton ModelNet (127,915 models) in computer vision research. MedShapeNet is created as an alternative to these commonly used shape benchmarks to facilitate the translation of data-driven vision algorithms to medical applications, and it extends the opportunities to adapt SOTA vision algorithms to solve critical medical problems. Besides, the majority of the medical shapes in MedShapeNet are modeled directly on the imaging data of real patients, and therefore it complements well existing shape benchmarks comprising of computer-aided design (CAD) models. MedShapeNet currently includes more than 100,000 medical shapes, and provides annotations in the form of paired data. It is therefore also a freely available repository of 3D models for extended reality (virtual reality - VR, augmented reality - AR, mixed reality - MR) and medical 3D printing. This white paper describes in detail the motivations behind MedShapeNet, the shape acquisition procedures, the use cases, as well as the usage of the online shape search portal: https://medshapenet.ikim.nrw/

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.

3DTeethSeg'22: 3D Teeth Scan Segmentation and Labeling Challenge

Teeth localization, segmentation, and labeling from intra-oral 3D scans are essential tasks in modern dentistry to enhance dental diagnostics, treatment planning, and population-based studies on oral health. However, developing automated algorithms for teeth analysis presents significant challenges due to variations in dental anatomy, imaging protocols, and limited availability of publicly accessible data. To address these challenges, the 3DTeethSeg'22 challenge was organized in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2022, with a call for algorithms tackling teeth localization, segmentation, and labeling from intraoral 3D scans. A dataset comprising a total of 1800 scans from 900 patients was prepared, and each tooth was individually annotated by a human-machine hybrid algorithm. A total of 6 algorithms were evaluated on this dataset. In this study, we present the evaluation results of the 3DTeethSeg'22 challenge. The 3DTeethSeg'22 challenge code can be accessed at: https://github.com/abenhamadou/3DTeethSeg22_challenge

Teeth3DS: a benchmark for teeth segmentation and labeling from intra-oral 3D scans

Teeth segmentation and labeling are critical components of Computer-Aided Dentistry (CAD) systems. Indeed, before any orthodontic or prosthetic treatment planning, a CAD system needs to first accurately segment and label each instance of teeth visible in the 3D dental scan, this is to avoid time-consuming manual adjustments by the dentist. Nevertheless, developing such an automated and accurate dental segmentation and labeling tool is very challenging, especially given the lack of publicly available datasets or benchmarks. This article introduces the first public benchmark, named Teeth3DS, which has been created in the frame of the 3DTeethSeg 2022 MICCAI challenge to boost the research field and inspire the 3D vision research community to work on intra-oral 3D scans analysis such as teeth identification, segmentation, labeling, 3D modeling and 3D reconstruction. Teeth3DS is made of 1800 intra-oral scans (23999 annotated teeth) collected from 900 patients covering the upper and lower jaws separately, acquired and validated by orthodontists/dental surgeons with more than 5 years of professional experience.

Vertebrae segmentation, identification and localization using a graph optimization and a synergistic cycle

This paper considers the segmentation, identification and localization of vertebrae in CT images. Although these three tasks are related, they face specific problems that add up when they are addressed together. For example neighboring vertebrae with similar shapes perturb the identification and vertebrae with complex or even pathological morphologies impact the segmentation. Consequently, the three tasks tend to be approached independently, e.g. labelling (localization and identification) or segmenting only, or, when treated globally, a sequential strategy is used. Sequential methods however are prone to accumulate errors as they are not able to recover from mistakes of the previous module. In this work, we propose to combine all three tasks and leverage their interdependence: locations ease the segmentation, the segmentations in turn improve the locations and they all contribute and benefit from the identification task. To this purpose we propose a virtuous cycle to enforce coherence between the three tasks. Within such a cycle, the tasks interoperate and are iterated until a global consistency criterion is satisfied. Our experiments validate this strategy with anatomically coherent results that outperform the state of the art on the VerSe20 challenge benchmark. Our code and model are openly available for research purposes at https://gitlab.inria.fr/spine/vertebrae_segmentation.

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.

3D Human Shape Style Transfer

We consider the problem of modifying/replacing the shape style of a real moving character with those of an arbitrary static real source character. Traditional solutions follow a pose transfer strategy, from the moving character to the source character shape, that relies on skeletal pose parametrization. In this paper, we explore an alternative approach that transfers the source shape style onto the moving character. The expected benefit is to avoid the inherently difficult pose to shape conversion required with skeletal parametrization applied on real characters. To this purpose, we consider image style transfer techniques and investigate how to adapt them to 3D human shapes. Adaptive Instance Normalisation (AdaIN) and SPADE architectures have been demonstrated to efficiently and accurately transfer the style of an image onto another while preserving the original image structure. Where AdaIN contributes with a module to perform style transfer through the statistics of the subjects and SPADE contribute with a residual block architecture to refine the quality of the style transfer. We demonstrate that these approaches are extendable to the 3D shape domain by proposing a convolutional neural network that applies the same principle of preserving the shape structure (shape pose) while transferring the style of a new subject shape. The generated results are supervised through a discriminator module to evaluate the realism of the shape, whilst enforcing the decoder to synthesise plausible shapes and improve the style transfer for unseen subjects. Our experiments demonstrate an average of $\approx 56\%$ qualitative and quantitative improvements over the baseline in shape transfer through optimization-based and learning-based methods.