In this paper, we present a patch-based representation of surfaces, PolyFit, which is obtained by fitting jet functions locally on surface patches. Such a representation can be learned efficiently in a supervised fashion from both analytic functions and real data. Once learned, it can be generalized to various types of surfaces. Using PolyFit, the surfaces can be efficiently deformed by updating a compact set of jet coefficients rather than optimizing per-vertex degrees of freedom for many downstream tasks in computer vision and graphics. We demonstrate the capabilities of our proposed methodologies with two applications: 1) Shape-from-template (SfT): where the goal is to deform the input 3D template of an object as seen in image/video. Using PolyFit, we adopt test-time optimization that delivers competitive accuracy while being markedly faster than offline physics-based solvers, and outperforms recent physicsguided neural simulators in accuracy at modest additional runtime. 2) Garment draping. We train a self-supervised, mesh- and garment-agnostic model that generalizes across resolutions and garment types, delivering up to an order-ofmagnitude faster inference than strong baselines.

We present FNOpt, a self-supervised cloth simulation framework that formulates time integration as an optimization problem and trains a resolution-agnostic neural optimizer parameterized by a Fourier neural operator (FNO). Prior neural simulators often rely on extensive ground truth data or sacrifice fine-scale detail, and generalize poorly across resolutions and motion patterns. In contrast, FNOpt learns to simulate physically plausible cloth dynamics and achieves stable and accurate rollouts across diverse mesh resolutions and motion patterns without retraining. Trained only on a coarse grid with physics-based losses, FNOpt generalizes to finer resolutions, capturing fine-scale wrinkles and preserving rollout stability. Extensive evaluations on a benchmark cloth simulation dataset demonstrate that FNOpt outperforms prior learning-based approaches in out-of-distribution settings in both accuracy and robustness. These results position FNO-based meta-optimization as a compelling alternative to previous neural simulators for cloth; thus reducing the need for curated data and improving cross-resolution reliability. Our code is publicly available at https://github.com/Simonhfls/FNOpt.

We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed surfaces as atlases computed by a neural network, which enables us to establish correspondences between frames. The key to making these correspondences semantically meaningful is to guarantee that the metric tensors computed at corresponding points are as similar as possible. We have devised an optimization strategy that makes our method robust to noise and global motions, without a priori correspondences or pre-alignment steps. As a result, our approach outperforms state-of-the-art ones on several challenging datasets.

Non-rigid structure-from-motion (NRSfM), a promising technique for addressing the mapping challenges in monocular visual deformable simultaneous localization and mapping (SLAM), has attracted growing attention. We introduce a novel method, called Con-NRSfM, for NRSfM under conformal deformations, encompassing isometric deformations as a subset. Our approach performs point-wise reconstruction using 2D selected image warps optimized through a graph-based framework. Unlike existing methods that rely on strict assumptions, such as locally planar surfaces or locally linear deformations, and fail to recover the conformal scale, our method eliminates these constraints and accurately computes the local conformal scale. Additionally, our framework decouples constraints on depth and conformal scale, which are inseparable in other approaches, enabling more precise depth estimation. To address the sensitivity of the formulated problem, we employ a parallel separable iterative optimization strategy. Furthermore, a self-supervised learning framework, utilizing an encoder-decoder network, is incorporated to generate dense 3D point clouds with texture. Simulation and experimental results using both synthetic and real datasets demonstrate that our method surpasses existing approaches in terms of reconstruction accuracy and robustness. The code for the proposed method will be made publicly available on the project website:https://sites.google.com/view/con-nrsfm.

Recent neural, physics-based modeling of garment deformations allows faster and visually aesthetic results as opposed to the existing methods. Material-specific parameters are used by the formulation to control the garment inextensibility. This delivers unrealistic results with physically implausible stretching. Oftentimes, the draped garment is pushed inside the body which is either corrected by an expensive post-processing, thus adding to further inconsistent stretching; or by deploying a separate training regime for each body type, restricting its scalability. Additionally, the flawed skinning process deployed by existing methods produces incorrect results on loose garments. In this paper, we introduce a geometrical constraint to the existing formulation that is collision-aware and imposes garment inextensibility wherever possible. Thus, we obtain realistic results where draped clothes stretch only while covering bigger body regions. Furthermore, we propose a geometry-aware garment skinning method by defining a body-garment closeness measure which works for all garment types, especially the loose ones. Our code is publicly available at https://github.com/Simonhfls/GAPS.

A recent trend in Non-Rigid Structure-from-Motion (NRSfM) is to express local, differential constraints between pairs of images, from which the surface normal at any point can be obtained by solving a system of polynomial equations. While this approach is more successful than its counterparts relying on global constraints, the resulting methods face two main problems: First, most of the equation systems they formulate are of high degree and must be solved using computationally expensive polynomial solvers. Some methods use polynomial reduction strategies to simplify the system, but this adds some phantom solutions. In any event, an additional mechanism is employed to pick the best solution, which adds to the computation without any guarantees on the reliability of the solution. Second, these methods formulate constraints between a pair of images. Even if there is enough motion between them, they may suffer from local degeneracies that make the resulting estimates unreliable without any warning mechanism. %Unfortunately, these systems are of high degree with up to five real solutions. Hence, a computationally expensive strategy is required to select a unique solution. Furthermore, they suffer from degeneracies that make the resulting estimates unreliable, without any mechanism to identify this situation. In this paper, we solve these problems for isometric/conformal NRSfM. We show that, under widely applicable assumptions, we can derive a new system of equations in terms of the surface normals, whose two solutions can be obtained in closed-form and can easily be disambiguated locally. Our formalism also allows us to assess how reliable the estimated local normals are and to discard them if they are not. Our experiments show that our reconstructions, obtained from two or more views, are significantly more accurate than those of state-of-the-art methods, while also being faster. %In this paper, we show that, under widely applicable assumptions, we can derive a new system of equations in terms of the surface normals, whose two solutions can be obtained in closed-form and can easily be disambiguated locally. Our formalism also allows us to assess how reliable the estimated local normals are and to discard them if they are not. Our experiments show that our reconstructions, obtained from two or more views, are significantly more accurate than those of state-of-the-art methods, while also being faster.

In this paper, we tackle the problem of static 3D cloth draping on virtual human bodies. We introduce a two-stream deep network model that produces a visually plausible draping of a template cloth on virtual 3D bodies by extracting features from both the body and garment shapes. Our network learns to mimic a physics-based simulation (PBS) method while requiring two orders of magnitude less computation time. To train the network, we introduce loss terms inspired by PBS to produce plausible results and make the model collision-aware. To increase the details of the draped garment, we introduce two loss functions that penalize the difference between the curvature of the predicted cloth and PBS. Particularly, we study the impact of mean curvature normal and a novel detail-preserving loss both qualitatively and quantitatively. Our new curvature loss computes the local covariance matrices of the 3D points, and compares the Rayleigh quotients of the prediction and PBS. This leads to more details while performing favorably or comparably against the loss that considers mean curvature normal vectors in the 3D triangulated meshes. We validate our framework on four garment types for various body shapes and poses. Finally, we achieve superior performance against a recently proposed data-driven method.

Non-Rigid Structure-from-Motion (NRSfM) reconstructs a deformable 3D object from keypoint correspondences established between monocular 2D images. Current NRSfM methods lack statistical robustness, which is the ability to cope with correspondence errors. This prevents one to use automatically established correspondences, which are prone to errors, thereby strongly limiting the scope of NRSfM. We propose a three-step automatic pipeline to solve NRSfM robustly by exploiting isometry. Step (i) computes the optical flow from correspondences, step (ii) reconstructs each 3D point's normal vector using multiple reference images and integrates them to form surfaces with the best reference and step (iii) rejects the 3D points that break isometry in their local neighborhood. Importantly, each step is designed to discard or flag erroneous correspondences. Our contributions include the robustification of optical flow by warp estimation, new fast analytic solutions to local normal reconstruction and their robustification, and a new scale-independent measure of 3D local isometric coherence. Experimental results show that our robust NRSfM method consistently outperforms existing methods on both synthetic and real datasets.

We propose a method for the unsupervised reconstruction of a temporally-coherent sequence of surfaces from a sequence of time-evolving point clouds, yielding dense, semantically meaningful correspondences between all keyframes. We represent the reconstructed surface as an atlas, using a neural network. Using canonical correspondences defined via the atlas, we encourage the reconstruction to be as isometric as possible across frames, leading to semantically-meaningful reconstruction. Through experiments and comparisons, we empirically show that our method achieves results that exceed that state of the art in the accuracy of unsupervised correspondences and accuracy of surface reconstruction.

Monocular simultaneous localization and mapping (SLAM) algorithms perform robustly when observing rigid scenes; however, they fail when the observed scene deforms, for example, in medical endoscopy applications. In this article, we present DefSLAM, the first monocular SLAM capable of operating in deforming scenes in real time. Our approach intertwines Shape-from-Template (SfT) and Non-Rigid Structure-from-Motion (NRSfM) techniques to deal with the exploratory sequences typical of SLAM. A deformation tracking thread recovers the pose of the camera and the deformation of the observed map, at frame rate, by means of SfT processing a template that models the scene shape-at-rest. A deformation mapping thread runs in parallel with the tracking to update the template, at keyframe rate, by means of an isometric NRSfM processing a batch of full perspective keyframes. In our experiments, DefSLAM processes close-up sequences of deforming scenes, both in a laboratory-controlled experiment and in medical endoscopy sequences, producing accurate 3-D models of the scene with respect to the moving camera.

Generative models that produce point clouds have emerged as a powerful tool to represent 3D surfaces, and the best current ones rely on learning an ensemble of parametric representations. Unfortunately, they offer no control over the deformations of the surface patches that form the ensemble and thus fail to prevent them from either overlapping or collapsing into single points or lines. As a consequence, computing shape properties such as surface normals and curvatures becomes difficult and unreliable. In this paper, we show that we can exploit the inherent differentiability of deep networks to leverage differential surface properties during training so as to prevent patch collapse and strongly reduce patch overlap. Furthermore, this lets us reliably compute quantities such as surface normals and curvatures. We will demonstrate on several tasks that this yields more accurate surface reconstructions than the state-of-the-art methods in terms of normals estimation and amount of collapsed and overlapped patches.

We propose a new formulation to the non-rigid structure-from-motion problem that only requires the deforming surface to meaning that its differential structure is preserved. This is a much weaker assumption than the traditional ones of isometry or conformality. We show that it is nevertheless sufficient to establish local correspondences between the surface in two different images and therefore to perform point-wise reconstruction using only up to first-order derivatives. We formulate differential constraints and solve them algebraically using the theory of resultants. We will demonstrate that our approach is more widely applicable, more stable in noisy and sparse imaging conditions and much faster than earlier ones, while delivering similar accuracy. The code is available at https//github.com/cvlab-epf1/diff-nrsfm/.

3D reconstruction of deformable objects using inter-image visual motion from monocular images has been studied under Shape-from-Template (SfT) and Non-Rigid Structure-from-Motion (NRSfM). Most methods have been developed for simple deformation models, primarily isometry. They may treat a surface as a discrete set of points and draw constraints from the points only or they may use a non-parametric representation and use both points and differentials to express constraints. We propose a differential framework based on Cartan's theory of connections and moving frames. It is applicable to SfT and NRSfM, and to deformation models other than isometry. It utilises infinitesimal-level assumptions on the surface's geometry and mappings. It has the following properties. 1) It allows one to derive existing solutions in a simpler way. 2) It models SfT and NRSfM in a unified way. 3) It allows us to introduce a new skewless deformation model and solve SfT and NRSfM for it. 4) It facilitates a generic solution to SfT which does not require deformation modeling. Our framework is complete: it solves deformable 3D reconstruction for a whole class of algebraic deformation models including isometry. We compared our solutions with the state-of-the-art methods and show that ours outperform in terms of both accuracy and computation time.

We study Isometric Non-Rigid Shape-from-Motion (Iso-NRSfM): given multiple intrinsically calibrated monocular images, we want to reconstruct the time-varying 3D shape of a thin-shell object undergoing isometric deformations. We show that Iso-NRSfM is solvable from local warps, the inter-image geometric transformations. We propose a new theoretical framework based on the Riemmanian manifold to represent the unknown 3D surfaces as embeddings of the camera's retinal plane. This allows us to use the manifold's metric tensor and Christoffel Symbol (CS) fields. These are expressed in terms of the first and second order derivatives of the inverse-depth of the 3D surfaces, which are the unknowns for Iso-NRSfM. We prove that the metric tensor and the CS are related across images by simple rules depending only on the warps. This forms a set of important theoretical results. We show that current solvers cannot solve for the first and second order derivatives of the inverse-depth simultaneously. We thus propose an iterative solution in two steps. 1) We solve for the first order derivatives assuming that the second order derivatives are known. We initialise the second order derivatives to zero, which is an infinitesimal planarity assumption. We derive a system of two cubics in two variables for each image pair. The sum-of-squares of these polynomials is independent of the number of images and can be solved globally, forming a well-posed problem for $N\geq 3$ images. 2) We solve for the second order derivatives by initialising the first order derivatives from the previous step. We solve a linear system of $4N-4$ equations in three variables. We iterate until the first order derivatives converge. The solution for the first order derivatives gives the surfaces' normal fields which we integrate to recover the 3D surfaces. The proposed method outperforms existing work in terms of accuracy and computation cost on synthetic and real datasets.

We study Isometric Non-Rigid Shape-from-Motion (Iso-NRSfM): given multiple intrinsically calibrated monocular images, we want to reconstruct the time-varying 3D shape of an object undergoing isometric deformations. We show that Iso-NRSfM is solvable from the warps (the inter-image geometric transformations). We propose a new theoretical framework based on Riemmanian manifolds to represent the unknown 3D surfaces, as embeddings of the camera's retinal planes. This allows us to use the manifolds' metric tensor and Christoffel Symbol fields, which we prove are related across images by simple rules depending only on the warps. This forms a set of important theoretical results. Using the infinitesimal planarity formulation, it then allows us to derive a system of two quartics in two variables for each image pair. The sum-of-squares of these polynomials is independent of the number of images and can be solved globally, forming a well-posed problem for N ≥ 3 images, whose solution directly leads to the surface's normal field. The proposed method outperforms existing work in terms of accuracy and computation cost on synthetic and real datasets.

The objective of Shape-from-Template (SfT) is to infer an object's shape from a single image and a 3D object template. Existing methods are called thin-shell SfT as they represent the object by its outer surface. This may be an open surface for thin objects such as a piece of paper or a closed surface for thicker objects such as a ball. We propose volumetric SfT, which specifically handles objects of the latter kind. Volumetric SfT uses the object's full volume to express the deformation constraints and reconstructs the object's surface and interior deformation. This is a challenging problem because for opaque objects, only a part of the outer surface is visible in the image. Inspired by mesh-editing techniques, we use an As-Rigid-As-Possible (ARAP) deformation model that softly imposes local rigidity. We formalise ARAP isometric SfT as a constrained variational optimisation problem which we solve using iterative optimisation. We present strategies to find an initial solution based on thin-shell SfT and volume propagation. Experiments with synthetic and real data show that our method has a typical maximum relative error of 5% in reconstructing the deformation of an entire object, including its back and interior for which no visual data is available.