SDF-based differential rendering frameworks have achieved state-of-the-art multiview 3D shape reconstruction. In this work, we re-examine this family of approaches by minimally reformulating its core appearance model in a way that simultaneously yields faster computation and increased performance. To this goal, we exhibit a physically-inspired minimal radiance parametrization decoupling angular and spatial contributions, by encoding them with a small number of features stored in two respective volumetric grids of different resolutions. Requiring as little as four parameters per voxel, and a tiny MLP call inside a single fully fused kernel, our approach allows to enhance performance with both surface and image (PSNR) metrics, while providing a significant training speedup and real-time rendering. We show this performance to be consistently achieved on real data over two widely different and popular application fields, generic object and human subject shape reconstruction, using four representative and challenging datasets.1

Volumetric shape representations have become ubiquitous in multi-view reconstruction tasks. They often build on regular voxel grids as discrete representations of 3D shape functions, such as SDF or radiance fields, either as the full shape model or as sampled instantiations of continuous representations, as with neural networks. Despite their proven efficiency, voxel representations come with the precision versus complexity trade-off. This inherent limitation can significantly impact performance when moving away from simple and uncluttered scenes. In this paper we investigate an alternative discretization strategy with the Centroidal Voronoi Tessellation (CVT). CVTs allow to better partition the observation space with respect to shape occupancy and to focus the discretization around shape surfaces. To leverage this discretization strategy for multi-view reconstruction, we introduce a volumetric optimization framework that combines explicit SDF fields with a shallow color network, in order to estimate 3D shape properties over tetrahedral grids. Experimental results with Chamfer statistics validate this approach with unprecedented reconstruction quality on various scenarios such as objects, open scenes or human.

We present a data-driven framework for unsupervised human motion retargeting that animates a target subject with the motion of a source subject. Our method is correspondence-free, requiring neither spatial correspondences between the source and target shapes nor temporal correspondences between different frames of the source motion. This allows to animate a target shape with arbitrary sequences of humans in motion, possibly captured using $4 D$ acquisition platforms or consumer devices. Our method unifies the advantages of two existing lines of work, namely skeletal motion retargeting, which leverages long-term temporal context, and surface-based retargeting, which preserves surface details, by combining a geometry-aware deformation model with a skeleton-aware motion transfer approach. This allows to take into account long-term temporal context while accounting for surface details. During inference, our method runs online, i.e. 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 for skeletal motion and detail preservation. Furthermore, our method generalizes to unobserved motions and body shapes. We demonstrate that our method achieves state-of-the-art results on two test datasets and that it can be used to animate human models with the output of a multi-view acquisition platform. Code is available at https://gitlab.inria.fr/rrekikdi/humanmotion-retargeting2023.

International audience

In this paper, we investigate how to complete human body shape models by combining shape and flow estimation given two consecutive depth images. Shape completion is a challenging task in computer vision that is highly under-constrained when considering partial depth observations. Besides model based strategies that exploit strong priors, and consequently struggle to preserve fine geometric details, learning based approaches build on weaker assumptions and can benefit from efficient implicit representations. We adopt such a representation and explore how the motion flow between two consecutive frames can contribute to the shape completion task. In order to effectively exploit the flow information, our architecture combines both estimations and implements two features for robustness: First, an all-to-all attention module that encodes the correlation between points in the same frame and between corresponding points in different frames; Second, a coarse-dense to fine-sparse strategy that balances the representation ability and the computational cost. Our experiments demonstrate that the flow actually benefits human body model completion. They also show that our method outperforms the state-of-the-art approaches for shape completion on 2 benchmarks, considering different human shapes, poses, and clothing.

We propose a framework to learn a structured latent space to represent 4D human body motion, where each latent vector encodes a full motion of the whole 3D human shape. On one hand several data-driven skeletal animation models exist proposing motion spaces of temporally dense motion signals, but based on geometrically sparse kinematic representations. On the other hand many methods exist to build shape spaces of dense 3D geometry, but for static frames. We bring together both concepts, proposing a motion space that is dense both temporally and geometrically. Once trained, our model generates a multi-frame sequence of dense 3D meshes based on a single point in a low-dimensional latent space. This latent space is built to be structured, such that similar motions form clusters. It also embeds variations of duration in the latent vector, allowing semantically close sequences that differ only by temporal unfolding to share similar latent vectors. We demonstrate experimentally the structural properties of our latent space, and show it can be used to generate plausible interpolations between different actions. We also apply our model to 4D human motion completion, showing its promising abilities to learn spatiotemporal features of human motion. Code is available at https://github.com/mmarsot/A_structured_latent_space.

Differential rendering has recently emerged as a powerful tool for image-based rendering or geometric reconstruction from multiple views, with very high quality. Up to now, such methods have been benchmarked on generic object databases and promisingly applied to some real data, but have yet to be applied to specific applications that may benefit. In this paper, we investigate how a differential rendering system can be crafted for raw multi-camera performance capture. We address several key issues in the way of practical usability and reproducibility, such as processing speed, explainability of the model, and general output model quality. This leads us to several contributions to the differential rendering framework. In particular we show that a unified view of differential rendering and classic optimization is possible, leading to a formulation and implementation where complete non-stochastic gradient steps can be analytically computed and the full perframe data stored in video memory, yielding a straight-forward and efficient implementation. We also use a sparse storage and coarse-to-fine scheme to achieve extremely high resolution with contained memory and computation time. We show that results rivaling or exceeding the quality of state of the art multi-view human surface capture methods are achievable in a fraction of the time, typically around a minute per frame.

Measuring contact friction in soft-bodies usually requires a specialised physics bench and a tedious acquisition protocol. This makes the prospect of a purely non-invasive, video-based measurement technique particularly attractive. Previous works have shown that such a video-based estimation is feasible for material parameters using deep learning, but this has never been applied to the friction estimation problem which results in even more subtle visual variations. Because acquiring a large dataset for this problem is impractical, generating it from simulation is the obvious alternative. However, this requires the use of a frictional contact simulator whose results are not only visually plausible, but physically-correct enough to match observations made at the macroscopic scale. In this paper, which is an extended version of our former work A. H. Rasheed, V. Romero, F. Bertails-Descoubes, S. Wuhrer, J.-S. Franco, and A Lazarus, "Learning to measure the static friction coefficient in cloth contact," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., 2020, pp. 9909-9918, we propose to our knowledge the first non-invasive measurement network and adjoining synthetic training dataset for estimating cloth friction at contact, for both cloth-hard body and cloth-cloth contacts. To this end we build a protocol for validating and calibrating a state-of-the-art frictional contact simulator, in order to produce a reliable dataset. We furthermore show that without our careful calibration procedure, the training fails to provide accurate estimation results on real data. We present extensive results on a large acquired test set of several hundred real video sequences of cloth in friction, which validates the proposed protocol and its accuracy.

We examine the problem of mesh denoising, which consists of removing noise from corrupted 3D meshes while preserving existing geometric features. Most mesh denoising methods require a lot of mesh-specific parameter fine-tuning, to account for specific features and noise types. In recent years, data-driven methods have demonstrated their robustness and effectiveness with respect to noise and feature properties on a wide variety of geometry and image problems. Most existing mesh denoising methods still use hand-crafted features, and locally denoise facets rather than examine the mesh globally. In this work, we propose the use of a fully end-to-end learning strategy based on graph convolutions, where meaningful features are learned directly by our network. It operates on a graph of facets, directly on the existing topology of the mesh, without resampling, and follows a multi-scale design to extract geometric features at different resolution levels. Similar to most recent pipelines, given a noisy mesh, we first denoise face normals with our novel approach, then update vertex positions accordingly. Our method performs significantly better than the current state-of-the-art learning-based methods. Additionally, we show that it can be trained on noisy data, without explicit correspondence between noisy and ground-truth facets. We also propose a multi-scale denoising strategy, better suited to correct noise with a low spatial frequency.

We address the problem of inferring a human shape from partial observations, such as depth images, in temporal sequences. Deep Neural Networks (DNN) have been shown successful to estimate detailed shapes on a frame-by-frame basis but consider yet little or no temporal information over frame sequences for detailed shape estimation. Recently, networks that implicitly encode shape occupancy using MLP layers have shown very promising results for such single-frame shape inference, with the advantage of reducing the dimensionality of the problem and providing continuously encoded results. In this work we propose to generalize implicit encoding to spatio-temporal shape inference with spatio-temporal implicit function networks or STIF-Nets, where temporal redundancy and continuity is expected to improve the shape and motion quality. To validate these added benefits, we collect and train with motion data from CAPE for dressed humans, and DFAUST for body shapes with no clothing. We show our model’s ability to estimate shapes for a set of input frames, and interpolate between them. Our results show that our method outpetforms existing state of the art methods, in particular the single-frame methods for detailed shape estimation.

Measuring friction coefficients between cloth and an external body is a longstanding issue in mechanical engineering, never yet addressed with a pure vision-based system. The latter offers the prospect of simpler, less invasive friction measurement protocols compared to traditional ones, and can vastly benefit from recent deep learning advances. Such a novel measurement strategy however proves challenging, as no large labelled dataset for cloth contact exists, and creating one would require thousands of physics workbench measurements with broad coverage of cloth-material pairs. Using synthetic data instead is only possible assuming the availability of a soft-body mechanical simulator with true-to-life friction physics accuracy, yet to be verified. We propose a first vision-based measurement network for friction between cloth and a substrate, using a simple and repeatable video acquisition protocol. We train our network on purely synthetic data generated by a state-of-the-art frictional contact simulator, which we carefully calibrate and validate against real experiments under controlled conditions. We show promising results on a large set of contact pairs between real cloth samples and various kinds of substrates, with 93.6% of all measurements predicted within 0.1 range of standard physics bench measurements.

In this paper we report on the representation of appearance information in the context of 3D multi-view shape modeling. Most applications in image based 3D modeling resort to texture maps, a 2D mapping of shape color information into image files. Despite their unquestionable merits, in particular the ability to apply standard image tools, including compression, image textures still suffer from limitations that result from the 2D mapping of information that originally belongs to a 3D structure. This is especially true with 2D texture atlases, a generic 2D mapping for 3D mesh models that introduces discontinuities in the texture space and plagues many 3D appearance algorithms. Moreover, the per-triangle texel density of 2D image textures cannot be individually adjusted to the corresponding pixel observation density without a global change in the atlas mapping function. To address these issues, we propose a new appearance representation for image-based 3D shape modeling, which stores appearance information directly on 3D meshes, rather than a texture atlas. We show this representation to allow for input-adaptive sampling and compression support. Our experiments demonstrate that it outperforms traditional image textures, in multi-view reconstruction contexts, with better visual quality and memory footprint, which makes it a suitable tool when dealing with large amounts of data as with dynamic scene 3D models.

In this paper, we tackle the problem of 3D human shape estimation from single RGB images. While the recent progress in convolutional neural networks has allowed impressive results for 3D human pose estimation, estimating the full 3D shape of a person is still an open issue. Model-based approaches can output precise meshes of naked under-cloth human bodies but fail to estimate details and un-modelled elements such as hair or clothing. On the other hand, non-parametric volumetric approaches can potentially estimate complete shapes but, in practice, they are limited by the resolution of the output grid and cannot produce detailed estimates. In this work, we propose a non-parametric approach that employs a double depth map to represent the 3D shape of a person: a visible depth map and a ``hidden'' depth map are estimated and combined, to reconstruct the human 3D shape as done with a ``mould''. This representation through 2D depth maps allows a higher resolution output with a much lower dimension than voxel-based volumetric representations. Additionally, our fully derivable depth-based model allows us to efficiently incorporate a discriminator in an adversarial fashion to improve the accuracy and ``humanness'' of the 3D output. We train and quantitatively validate our approach on SURREAL and on 3D-HUMANS, a new photorealistic dataset made of semi-synthetic in-house videos annotated with 3D ground truth surfaces.

3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences. Most current approaches follow the Iterative-Closest-Point (ICP) paradigm, where the association step is carried out by searching for the nearest neighbors. It fails when large deformations occur and errors in the association tend to propagate over time. In this paper, we propose a discriminative alternative for the association, that leverages random forests to infer correspondences in one shot. Regardless the choice of shape parameterizations, being surface or volumetric meshes, we convert 3D shapes to volumetric distance fields and thereby design features to train the forest. We investigate two ways to draw volumetric samples: voxels of regular grids and cells from Centroidal Voronoi Tessellation (CVT). While the former consumes considerable memory and in turn limits us to learn only subject-specific correspondences, the latter yields much less memory footprint by compactly tessellating the interior space of a shape with optimal discretization. This facilitates the use of larger cross-subject training databases, generalizes to different human subjects and hence results in less overfitting and better detection. The discriminative correspondences are successfully integrated to both surface and volumetric deformation frameworks that recover human shape poses, which we refer to as 'tracking-by-detection of 3D human shapes.' It allows for large deformations and prevents tracking errors from being accumulated. When combined with ICP for refinement, it proves to yield better accuracy in registration and more stability when tracking over time. Evaluations on existing datasets demonstrate the benefits with respect to the state-of-the-art.

We address the problem of transferring motion between captured 4D models. We particularly focus on human subjects for which the ability to automatically augment 4D datasets, by propagating movements between subjects, is of interest in a great deal of recent vision applications that builds on human visual corpus. Given 4D training sets for two subjects for which a sparse set of corresponding keyposes are known, our method is able to transfer a newly captured motion from one subject to the other. With the aim to generalize transfers to input motions possibly very diverse with respect to the training sets, the method contributes with a new transfer model based on non-linear pose interpolation. Building on Gaussian process regression, this model intends to capture and preserve individual motion properties, and thereby realism, by accounting for pose inter-dependencies during motion transfers. Our experiments show visually qualitative, and quantitative, improvements over existing pose-mapping methods and confirm the generalization capabilities of our method compared to state of the art.

We consider 4D shape reconstructions in multi-view environments and investigate how to exploit temporal redundancy for precision refinement. In addition to being beneficial to many dynamic multi-view scenarios this also enables larger scenes where such increased precision can compensate for the reduced spatial resolution per image frame. With precision and scalability in mind, we propose a symmetric (non-causal) local time-window geometric integration scheme over temporal sequences, where shape reconstructions are refined framewise by warping local and reliable geometric regions of neighboring frames to them. This is in contrast to recent comparable approaches targeting a different context with more compact scenes and real-time applications. These usually use a single dense volumetric update space or geometric template, which they causally track and update globally frame by frame, with limitations in scalability for larger scenes and in topology and precision with a template based strategy. Our templateless and local approach is a first step towards temporal shape super-resolution. We show that it improves reconstruction accuracy by considering multiple frames. To this purpose, and in addition to real data examples, we introduce a multi-camera synthetic dataset that provides ground-truth data for mid-scale dynamic scenes.

We address the problem of multi-view video segmentation of dynamic scenes in general and outdoor environments with possibly moving cameras. Multi-view methods for dynamic scenes usually rely on geometric calibration to impose spatial shape constraints between viewpoints. In this paper, we show that the calibration constraint can be relaxed while still getting competitive segmentation results using multi-view constraints. We introduce new multi-view cotemporality constraints through motion correlation cues, in addition to common appearance features used by co-segmentation methods to identify co-instances of objects. We also take advantage of learning based segmentation strategies by casting the problem as the selection of monocular proposals that satisfy multi-view constraints. This yields a fully automated method that can segment subjects of interest without any particular pre-processing stage. Results on several challenging outdoor datasets demonstrate the feasibility and robustness of our approach.

In this paper, we address the problem of temporal alignment of surfaces for subjects dressed in wide clothing, as acquired by calibrated multi-camera systems. Most existing methods solve the alignment by fitting a single surface template to each instant's 3D observations, relying on a dense point-to-point correspondence scheme, e.g. by matching individual surface points based on local geometric features or proximity. The wide clothing situation yields more geometric and topological difficulties in observed sequences, such as apparent merging of surface components, misreconstructions, and partial surface observation, resulting in overly sparse, erroneous point-to-point correspondences, and thus alignment failures. To resolve these issues, we propose an alignment framework where point-to-point correspondences are obtained by growing isometric patches from a set of reliably obtained body landmarks. This correspondence decreases the reliance on local geometric features subject to instability, instead emphasizing the surface neighborhood coherence of matches, while improving density given sufficient landmark coverage. We validate and verify the resulting improved alignment performance in our experiments.

In this paper, we propose a new framework for 3D tracking by detection based on fully volumetric representations. On one hand, 3D tracking by detection has shown robust use in the context of interaction (Kinect) and surface tracking. On the other hand, volumetric representations have recently been proven efficient both for building 3D features and for addressing the 3D tracking problem. We leverage these benefits by unifying both families of approaches into a single, fully volumetric tracking-by-detection framework. We use a centroidal Voronoi tessellation (CVT) representation to compactly tessellate shapes with optimal discretization, construct a feature space, and perform the tracking according to the correspondences provided by trained random forests. Our results show improved tracking and training computational efficiency and improved memory performance. This in turn enables the use of larger training databases than state of the art approaches, which we leverage by proposing a cross-tracking subject training scheme to benefit from all subject sequences for all tracking situations, thus yielding better detection and less overfitting.

Recovering 3D shape motion using visual information is an important problem with many applications in computer vision and computer graphics, among other domains. Most existing approaches rely on surface-based strategies, where surface models are fit to visual surface observations. While numerically plausible, this paradigm ignores the fact that the observed surfaces often delimit volumetric shapes, for which deformations are constrained by the volume in-side the shape. Consequently, surface-based strategies can fail when the observations define several feasible surfaces, whereas volumetric considerations are more restrictive with respect to the admissible solutions. In this work, we investigate a novel volumetric shape parametrization to track shapes over temporal sequences. In constrast to Eulerian grid discretizations of the observation space, such as voxels, we consider general shape tesselations yielding more convenient cell decompositions, in particular the Centroidal Voronoi Tesselation. With this shape representation, we devise a tracking method that exploits volumetric information, both for the data term evaluating observation conformity, and for expressing deformation constraints that enforce prior assumptions on motion. Experiments on several datasets demonstrate similar or improved precisions over state-of-the-art methods, as well as improved robustness, a critical issue when tracking sequentially over time frames.

Multiple view segmentation consists in segmenting objects simultaneously in several views. A key issue in that respect and compared to monocular settings is to ensure propagation of segmentation information between views while minimizing complexity and computational cost. In this work, we first investigate the idea that examining measurements at the projections of a sparse set of 3D points is sufficient to achieve this goal. The proposed algorithm softly assigns each of these 3D samples to the scene background if it projects on the background region in at least one view, or to the foreground if it projects on foreground region in all views. Second, we show how other modalities such as depth may be seamlessly integrated in the model and benefit the segmentation. The paper exposes a detailed set of experiments used to validate the algorithm, showing results comparable with the state of art, with reduced computational complexity. We also discuss the use of different modalities for specific situations, such as dealing with a low number of viewpoints or a scene with color ambiguities between foreground and background.

We examine the problem of retrieving high resolution textures of objects observed in multiple videos under small object deformations. In the monocular case, the data redundancy necessary to reconstruct a high-resolution image stems from temporal accumulation. This has been vastly explored and is known as image super-resolution. On the other hand, a handful of methods have considered the texture of a static 3D object observed from several cameras, where the data redundancy is obtained through the different viewpoints. We introduce a unified framework to leverage both possibilities for the estimation of an object's high resolution texture. This framework uniformly deals with any related geometric variability introduced by the acquisition chain or by the evolution over time. To this goal we use 2D warps for all viewpoints and all temporal frames and a linear image formation model from texture to image space. Despite its simplicity, the method is able to successfully handle different views over space and time. As shown experimentally, it demonstrates the interest of temporal information to improve the texture quality. Additionally, we also show that our method outperforms state of the art multi-view super-resolution methods existing for the static case.

In this paper, we address the problem of object segmentation in multiple views or videos when two or more viewpoints of the same scene are available. We propose a new approach that propagates segmentation coherence information in both space and time, hence allowing evidences in one image to be shared over the complete set. To this aim the segmentation is cast as a single efficient labeling problem over space and time with graph cuts. In contrast to most existing multi-view segmentation methods that rely on some form of dense reconstruction, ours only requires a sparse 3D sampling to propagate information between viewpoints. The approach is thoroughly evaluated on standard multi-view datasets, as well as on videos. With static views, results compete with state of the art methods but they are achieved with significantly fewer viewpoints. With multiple videos, we report results that demonstrate the benefit of segmentation propagation through temporal cues.

We present a novel probabilistic framework for rigid tracking and segmentation of shapes observed from multiple cameras. Most existing methods have focused on solving each of these problems individually, segmenting the shape assuming surface registration is solved, or conversely performing surface registration assuming shape segmentation or kinematic structure is known. We assume no prior kinematic or registration knowledge except for an over-estimate k of the number of rigidities in the scene, instead proposing to simultaneously discover, adapt, and track its rigid structure on the fly. We simultaneously segment and infer poses of rigid subcomponents of a single chosen reference mesh acquired in the sequence. We show that this problem can be rigorously cast as a likelihood maximization over rigid component parameters. We solve this problem using an Expectation Maximization algorithm, with latent observation assignments to reference vertices and rigid parts. Our experiments on synthetic and real data show the validity of the method, robustness to noise, and its promising applicability to complex sequences.

In this paper we investigate shape and motion retrieval in the context of multi-camera systems. We propose a new low-level analysis based on latent silhouette cues, particularly suited for low-texture and outdoor datasets. Our analysis does not rely on explicit surface representations, instead using an EM framework to simultaneously update a set of volumetric voxel occupancy probabilities and retrieve a best estimate of the dense 3D motion field from the last consecutively observed multi-view frame set. As the framework uses only latent, probabilistic silhouette information, the method yields a promising 3D scene analysis method robust to many sources of noise and arbitrary scene objects. It can be used as input for higher level shape modeling and structural inference tasks. We validate the approach and demonstrate its practical use for shape and motion analysis experimentally.

Networked virtual environments like Second Life enable distant people to meet for leisure as well as work. But users are represented through avatars controlled by keyboards and mouses, leading to a low sense of presence especially regarding body language. Multi-camera real-time 3D modeling offers a way to ensure a significantly higher sense of presence. But producing quality geometries, well textured, and to enable distant user tele-presence in non trivial virtual environments is still a challenge today.

Modeling from silhouettes is a popular and useful topic in computer vision. Many methods exist to compute the surface of the visual hull from silhouettes, but few address the problem of ensuring sane topological properties of the surface, such as manifoldness. This article provides an efficient algorithm to compute such a surface in the form of a polyhedral mesh. It relies on a small number of geometric operations to compute a visual hull polyhedron in a single pass. Such simplicity enables the algorithm to combine the advantages of being fast, producing pixel-exact surfaces, and repeatably yield manifold and watertight polyhedra in general experimental conditions with real data, as verified with all datasets tested. The algorithm is fully described, its complexity analyzed and modeling results given.

This paper deals with the 3D shape estimation from silhouette cues of multiple moving objects in general indoor or outdoor 3D scenes with potential static obstacles, using multiple calibrated video streams. Most shape-from-silhouette techniques use a two-classification of space occupancy and silhouettes, based on image regions that match or disagree with a static background appearance model. Binary silhouette information becomes insufficient to unambiguously carve 3D space regions as the number and density of dynamic objects increases. In such difficult scenes, multi-view stereo methods suffer from visibility problems, and rely on color calibration procedures tedious to achieve outdoors. We propose a new algorithm to automatically detect and reconstruct scenes with a variable number of dynamic objects. Our formulation distinguishes between m different shapes in the scene by using automatically learnt view-specific appearance models, eliminating the color calibration requirement. Bayesian reasoning is then applied to solve the m-shape occupancy problem, with m updated as objects enter or leave the scene. Results show that this method yields multiple silhouette-based estimates that drastically improve scene reconstructions over traditional two-label silhouette scene analysis. This enables the method to also efficiently deal with multi-person tracking problems.

Real-time multi-camera 3D modeling provides full-body geometric and photometric data on the objects present in the acquisition space. It can be used as an input device for rendering textured 3D models, and for computing interactions with virtual objects through a physical simulation engine. In this paper we present a work in progress to build a collaborative environment where two distant users, each one 3D modeled in real-time, interact in a shared virtual world.

We consider the problem of detecting and accounting for the presence of occluders in a 3D scene based on silhouette cues in video streams obtained from multiple, calibrated views. While well studied and robust in controlled environments, silhouette-based reconstruction of dynamic objects fails in general environments where uncontrolled occlusions are commonplace, due to inherent silhouette corruption by occluders. We show that occluders in the interaction space of dynamic objects can be detected and their 3D shape fully recovered as a byproduct of shape-from-silhouette analysis. We provide a Bayesian sensor fusion formulation to process all occlusion cues occurring in a multi-view sequence. Results show that the shape of static occluders can be robustly recovered from pure dynamic object motion, and that this information can be used for online self-correction and consolidation of dynamic object shape reconstruction.

In this paper, we present a scalable architecture to compute, visualize and interact with 3D dynamic models of real scenes. This architecture is designed for mixed reality applications requiring such dynamic models, tele-immersion for instance. Our system consists in 3 main parts: the acquisition, based on standard firewire cameras; the computation, based on a distribution scheme over a cluster of PC and using a recent shape-from-silhouette algorithm which leads to optimally precise 3D models; the visualization, which is achieved on a multiple display wall. The proposed distribution scheme ensures scalability of the system and hereby allows control over the number of cameras used for acquisition, the frame-rate, or the number of projectors used for high resolution visualization. To our knowledge this is the first completely scalable vision architecture for real time 3D modeling, from acquisition to visualization through computation. Experimental results show that this framework is very promising for real time 3D interactions.

In this paper, we investigate what can be inferred from several silhouette probability maps, in multiview silhouette cue fusion. To this aim, we propose a new framework for multiview silhouette cue fusion. This framework work uses a space occupancy grid as a probabilistic 3D representation of scene contents. Such a representation is of great interest for various computer vision applications in perception, or localization for instance. Our main contribution is to introduce the occupancy grid concept, popular in the robotics, for multicamera environments. The idea is to consider each camera pixel as a statistical occupancy sensor. All pixel observations are then used jointly to infer where, and how likely, matter is present in the scene. As our results illustrate, this sample model has various advantages. Most sources of uncertainty are explicitly modeled, and no premature decisions about pixel labeling occur, thus preserving pixel knowledge. Consequently, optimal scene object localization, and robust volume reconstruction, can achieved, with no constraint on camera placement and object visibility. In addition, this representation allows to improve silhouette extraction in images

National audience

This paper addresses the problem of computing visual hulls from image contours. We propose a new hybrid approach, which overcomes the precision-complexity trade-off inherent to voxel based approaches by taking advantage of surface based approaches. To this aim, we introduce a space discretization, which does not rely on a regular grid where most cells are ineffective, but rather on an irregular grid where sample points lie on the surface of the visual hull. Such a grid is composed of tetrahedral cells obtained by applying a Delaunay triangulation on the sample points. These cells are carved afterward according to image silhouette information. The proposed approach keeps the robustness of volumetric approaches while drastically improving their precision and reducing their time and space complexities. It thus allows modeling of objects with complex geometry, and it also makes real time feasible for precise models. Preliminary results with synthetic and real data are presented.