Home
Publications
CV
Teaching

Maks Ovsjanikov's Publications

  Note: You can also find most up-to-date bib entries for my latest publications on the Google Scholar page.

Matteo Denitto, Simone Melzi, Manuele Bicego, Umberto Castellani, Alessandro Farinelli, Mário A. T. Figueiredo, Yanir Kleiman, Maks Ovsjanikov

We exploit the connection between biclustering and matching and use it to develop a new region-based correspondence algorithm, which: (i) casts the problem from a probabilistic low-rank matrix factorization perspective; (ii) uses a spike and slab prior to induce sparsity; (iii) is enriched with a spatial smoothness prior, encouraging nearby vertices to belong to the same bicluster... [paper preprint] [poster] [code demo] .

International Conference on Computer Vision (ICCV), 2017
Jing Ren, Jens Schneider, Maks Ovsjanikov and Peter Wonka

We present a novel approach for computing joint graph layouts and use it to visualize collections of segmented meshes. Our algorithm takes as input the set of graphs along with partial, possibly soft, correspondences between them and constructs a consistent embedding via an efficient two-stage optimization procedure... [paper preprint] [video] .

Transactions on Visualization and Computer Graphics (TVCG), 2017
Ruqi Huang and Maks Ovsjanikov

We propose to consider the adjoint operators of functional maps and demonstrate their utility in several tasks in geometry processing. Unlike a functional map, the adjoint operator reflects both the map and its distortion. We show that this property of the adjoint and its relation to map inverse can be used for bi-directional shape matching, functional map conversion, and for revealing distortion in shape collections... [paper preprint] [code]. Awarded the Replicability Stamp.

Computer Graphics Forum (proc. Symposium on Geometry Processing), 2017
Ruqi Huang, Frederic Chazal and Maks Ovsjanikov

In this paper, we provide stability guarantees for two frameworks that are based on the notion of functional maps - the shape difference operators and the techniques used to analyze and visualize the deformations between shapes. In theory, we formulate and rigorously justify the robustness that has been observed in practical implementations of those frameworks. Inspired by our theoretical results, we propose a pipeline for constructing shape difference operators on point clouds and show numerically that the results are robust and informative... [paper preprint].

Computer Graphics Forum 2017.
Omri Azencot, Etienne Corman, Mirela Ben-Chen and Maks Ovsjanikov

We propose a novel technique for computing consistent cross fields on a pair of triangle meshes given an input correspondence, which we use as guiding fields for approximately consistent quadrangulations. Unlike the majority of existing methods our approach does not assume that the meshes share the same connectivity or even have the same number of vertices, and furthermore does not place any restrictions on the topology (genus) of the shapes. We demonstrate that using the same formulation we can both compute a quadrangulation that would respect a given symmetry on the same shape or a map across a pair of shapes... [paper preprint].

Transactions on Graphics (Proc. SIGGRAPH) 2017.
Maks Ovsjanikov

This habilitation dissertation describes a set of approaches for analyzing and processing 3D shapes and their relations. The main unifying theme of this work is the observation that many concepts in geometric data analysis can be considered, both in theory and in practice, as linear operators acting on real-valued functions defined on the shapes... [HDR dissertation].

Habilitation à diriger des recherches (Université Paris-Sud), 2017.
Dorian Nogneng and Maks Ovsjanikov

We show that considering descriptors as linear operators acting on functions through multiplication, rather than as simple scalar-valued signals, allows to extract significantly more information from a given descriptor and ultimately results in a more accurate map estimation. Namely, we show that descriptor preservation constraints can be formulated via commutativity with respect to the unknown map, which can be encoded by considering relations between matrices in the discrete setting.... [paper preprint] [code demo].

Computer Graphics Forum (Proc. Eurographics) 2017.
Etienne Corman*, Justin Solomon*, Mirela Ben-Chen, Leonidas Guibas, Maks Ovsjanikov

We propose a novel way to capture and characterize distortion between shapes, by first showing that the discrete metric can be recovered from the previously proposed shape difference operators, by solving two linear systems of equations. We then introduce an extension of these operators using offset surfaces to capture extrinsic or embedding-dependent distortion. Finally, we prove that a set of four functional operators fully ecodes a shape up to rigid motion in both discrete and continuous settings, and provide a set of efficient optimization methods for shape recovery... [paper preprint]

*equal contribution
ACM Transactions on Graphics (TOG), presented at SIGGRAPH 2017.
Maks Ovsjanikov, Etienne Corman, Michael Bronstein, Emanuele Rodolà, Mirela Ben-Chen, Leonidas Guibas, Frederic Chazal, Alex Bronstein.

These course notes introduce the audience to the techniques for computing and processing correspondences between geometric objects, such as 3D shapes, images or point clouds based on the functional map framework. We provide the mathematical background, computational methods and various applications of this framework. [course notes] [SIGGRAPH 2017 course website] [SIGGRAPH Asia 2016 course website].

Proc. SIGGRAPH 2017 and SIGGRAPH Asia 2016 courses.
Moos Hueting, Viorica Pătrăucean, Maks Ovsjanikov, Niloy Mitra

In this paper, we propose the concept of a scene map, a coarse scene representation, which describes the locations of the objects present in the scene from a top down view, as well as a pipeline to extract such a map from a single RGB image. To this end, we use a synthetic rendering pipeline and an adapted architecture that learns a mapping from an input image to a scene map through the use of a deep neural network... [paper] [webpage] [code] .

Proc. VMV - Vision, Modeling and Visualization, 2016.
Vignesh Ganapathi-Subramanian, Boris Thibert, Maks Ovsjanikov, Leonidas Guibas

We propose a method to build correspondences between regions or parts of 3D models that are related but not necessarily very similar. We first build an affinity matrix between points on the two shapes, based on feature rank similarity over many feature functions, and then extract a family of corresponding maximally stable regions between the two shapes... [paper] [code demo].

Computer Graphics Forum (proc. Symposium on Geometry Processing), 2016
Thomas Bonis, Maks Ovsjanikov, Steve Oudot and Frederic Chazal

We propose a novel pooling approach for shape classification and recognition using the bag-of-words pipeline, based on topological persistence. Our technique extends standard max-pooling and provides significantly more informative and spatially sensitive characterizations of the feature functions... [paper].

International Workshop on Computational Topology in Image Context, 2016
Moos Hueting, Maks Ovsjanikov, Niloy Mitra

We introduce a system for joint image-3D model processing that uses the complementary strengths of each data modality to facilitate analysis and exploration. We use it to improve the quality of text-based 3D model search, align the filtered 3D model collections, and re-sort image collections based on pose and shape attributes. ... [paper] [video] [webpage] [code] .

Transactions on Graphics (Proc. SIGGRAPH Asia), 2015
Mathieu Carrière, Steve Oudot and Maks Ovsjanikov

In this paper, we propose the first point descriptor that captures the topological structure of a shape as ‘seen’ from a single point, in a multiscale and provably stable way. We also demonstrate how a large class of topological signatures, including ours, can be mapped to vectors, opening the door to many classical analysis and learning methods. ... [paper]

Computer Graphics Forum (Proc. Symposium on Geometry Processing), 2015
Etienne Corman, Maks Ovsjanikov and Antonin Chambolle

We present a new method for non-rigid shape matching designed to enforce continuity of the resulting correspondence. In particular, starting from an arbitrary continuous map between two surfaces we find an optimal flow that makes the final correspondence operator as close as possible to the initial functional map... [paper] [code].

Computer Graphics Forum (Proc. Symposium on Geometry Processing), 2015
Luca Castelli Aleardi, Alexandre Nolin and Maks Ovsjanikov

We consider the problem of designing efficient iterative methods for solving linear systems, associated with Laplacian matrices of undirected graphs. In particular, we study a class of preconditioners, known as tree preconditioners, introduced by Vaidya, and propose a very simple modification to the basic tree preconditioner, which can significantly improve the performance of the iterative linear solvers both in theory (for special graph types) and in practice... [paper] [code].

14th International Symposium on Experimental Algorithms (SEA), 2015
Omri Azencot, Maks Ovsjanikov, Frederic Chazal and Mirela Ben-Chen

We consider the problem of computing the Levi-Civita covariant derivative on triangle meshes, and provide a simple, easy-to-implement discretization for which we demonstrate experimental convergence. We also formally show the imposibility of satisfying all of the properties of Levi-Civita connection in the discrete setting and introduce linear operators, discretizing in particular the parallel transport as a certain matrix exponential. ... [paper] [supplemental]

Transactions on Graphics (TOG), presented at SIGGRAPH, 2015
Viorica Pătrăucean and Maks Ovsjanikov

In this paper, we propose a simple and efficient scheme for object instance recognition that can cover a of full affine transformations. Remarkably, although 3 feature pairs are necessary to define a unique affine transformation, we show how a quadratic data structure can be used without any loss of information within the BoW model... [paper]

IAPR International Conference on Machine Vision Applications (MVA), 2015
Etienne Corman, Maks Ovsjanikov, Antonin Chambolle

We present a novel method for computing correspondences between pairs of non-rigid shapes. Unlike the majority of existing techniques that assume a deformation model, we consider the problem of learning a correspondence model given a collection of reference pairs with known mappings between them, and show how this problem can be formalized and solved for efficiently using the functional maps framework ... [paper] [code].

Sixth Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment (NORDIA), Proc. ECCV Workshops, 2014
Omri Azencot, Steffen Weißmann, Maks Ovsjanikov, Max Wardetzky, Mirela Ben-Chen

We consider the problem of simulating the behavior of an incompressible fluid on a curved surface represented as an unstructured triangle mesh. We propose to model fluids using their vorticity, i.e., by a (time-varying) scalar function on the surface. The principles governing the behavior of this function can be described using a set of coupled linear operators ... [paper]

Computer Graphics Forum (Proc. Symposium on Geometry Processing), 2014
Fan Wang, Qixing Huang, Maks Ovsjanikov, Leonidas Guibas

In this paper, we present a method to jointly segment a set of images containing objects from multiple classes. We first establish consistent functional maps across the input images, and introduce a formulation that explicitly models partial similarity across images instead of global consistency... [paper]

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2014
Chunyuan Li, Maks Ovsjanikov and Frederic Chazal

We demonstrate that persistence diagrams built from functions defined on the objects can serve as compact and informative descriptors for images and shapes. Extensive experiments on 3D shape retrieval, hand gesture recognition and texture classification demonstrate that this approach can yield state-of-the-art performance when used with the bag-of-features... [paper]

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2014
Viorica Pătrăucean, Rafael Grompone von Gioi, Maks Ovsjanikov

We propose a novel approach for detecting partial reflectional symmetry in images. Our method uses a principled statistical procedure inspired from the a contrario theory to validate potential symmetries by minimizing the number of false positives.... [paper]

Symmetry Detection from Real World Images, CVPR 2013 Workshop
Omri Azencot, Mirela Ben-Chen, Frederic Chazal, Maks Ovsjanikov

We introduce a novel coordinate-free method for manipulating and analyzing vector fields on discrete surfaces. Unlike the commonly used representations of a vector field as an assignment of vectors to the faces of the mesh, or as real values on edges, we argue that vector fields can also be naturally viewed as operators... [paper] [code].

Computer Graphics Forum (Proceedings of SGP), 2013
Maks Ovsjanikov, Quentin Mérigot, Viorica Pătrăucean, Leonidas Guibas

In this paper, we consider the symmetric ambiguity problem present when matching shapes with intrinsic symmetries. Instead of sampling landmark correspondences, we address this problem directly by performing shape matching in an appropriate quotient space, where the symmetry has been identified and factored out... [paper]

Computer Graphics Forum (Proceedings of SGP), 2013
Raif Rustamov, Maks Ovsjanikov, Omri Azencot, Mirela Ben-Chen, Frederic Chazal, Leonidas Guibas

We develop a novel formulation for the notion of shape differences, aimed at providing detailed information about the location and nature of the differences or distortions between the two shapes being compared. Our difference operator, derived from a shape map... [paper]

ACM SIGGRAPH 2013
Maks Ovsjanikov, Mirela Ben-Chen, Frederic Chazal and Leonidas Guibas

In this paper we propose a method for analysing and visualizing individual maps between shapes, or collections of such maps. Unlike the majority of prior work, which focuses on discovering maps in the context of shape matching, our main focus is on evaluating, analysing and visualizing a given map, and the distortion(s) it introduces ... [paper]

Computer Graphics Forum (CGF), 2013.
Maks Ovsjanikov, Mirela Ben-Chen, Justin Solomon, Adrian Butscher and Leonidas Guibas

We present a novel representation of maps between pairs of shapes that allows for efficient inference and manipulation. Key to our approach is a generalization of the notion of map that puts in correspondence real-valued functions rather than points on the shapes... [paper] [code].

ACM SIGGRAPH 2012
Condition Number for Non-Rigid Shape Matching,
Maks Ovsjanikov, Qi-xing Huang and Leonidas Guibas

In this paper, we study the hardness of the problem of shape matching, and introduce the notion of the shape condition number, which captures the intuition that some shapes are inherently more difficult to match against than others, depending on their symmetry structure... [paper]

Comput. Graph. Forum 30(5) (Proc. Symposium on Geometry Processing 2011)
Exploration of Continuous Variability in Collections of 3D Shapes,
Maks Ovsjanikov, Wilmot Li, Leonidas Guibas and Niloy Mitra

We present a method for discovering and exploring continuous variability in a collection of 3D shapes without correspondences. Our method is based on a novel navigation interface that allows users to explore a collection of related shapes by deforming a base template.... [paper]

ACM SIGGRAPH 2011
Shape Google: Geometric words and expressions for invariant shape retrieval,
Alexander Bronstein, Michael Bronstein, Leonidas Guibas and Maks Ovsjanikov

In this article, we bring the spirit of feature-based computer vision approaches to the problem of nonrigid shape search and retrieval. Using multiscale diffusion heat kernels as "geometric words," we construct compact and informative shape descriptors... [paper] [code].

ACM Transactions on Graphics (TOG), 2011
Voronoi-based Curvature and Feature Estimation from Point Clouds,
Quentin Mérigot, Maks Ovsjanikov and Leonidas Guibas

We present an efficient and robust method for extracting curvature information, sharp features and normal directions of a piecewise smooth surface from its point cloud sampling in a unified framework... [paper] [code]

IEEE Transactions On Visualisation and Computer Graphics (TVCG), 2010
Topic Modeling for Personalized Recommendation of Volatile Items,
Maks Ovsjanikov and Ye Chen

We propose an efficient topic modeling framework in the presence of volatile dyadic observations when direct topic modeling is infeasible. We show both theoretically and empirically that often-available unstructured and semantically-rich meta-data can serve as a... [paper]

Proc. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), 2010
One Point Isometric Matching with the Heat Kernel,
Maks Ovsjanikov, Quentin Mérigot, Facundo Mémoli and Leonidas Guibas

In this paper, we show that under mild genericity conditions, a single correspondence can be used to recover an isometry defined on entire shapes, and thus the space of all isometries can be parameterized by one correspondence between a pair of points. This result is general, and does not depend... [paper]

Computer Graphics Forum (Proc. Symposium on Geometry Processing), 2010
Persistence-based Segmentation of Deformable Shapes,
Primoz Skraba, Maks Ovsjanikov, Frederic Chazal and Leonidas Guibas

In this paper, we combine two ideas: persistence-based clustering and the Heat Kernel Signature (HKS) function to obtain a multi-scale isometry invariant mesh segmentation algorithm. The key advantages of this approach is that it is tunable through a few intuitive parameters and is stable under near-isometric shape deformations... [paper] [code demo].

NORDIA Workshop, Proc. CVPR, 2010,
(Best Paper Award)
SHREC 2010: robust feature detection and description benchmark,
Alexander Bronstein, Michael Bronstein, Benjamin Bustos et al.

The benchmark tests the performance of shape feature detectors and descriptors under a wide variety of trans- formations... [paper]

Proc. Eurographics 2010 Workshop on 3D Object Retrieval (3DOR), 2010.
Image Webs: Computing and Exploiting Connectivity in Image Collections,
Kyle Heath, Natasha Gelfand, Maks Ovsjanikov, Mridul Aanjaneya, Leonidas Guibas

The focus of this paper is to study the large-scale connectivity of image collections and the use of this connectivity in a variety of applications... [paper]

Proc. Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
Meshless Shape and Motion Design for Multiple Deformable Objects,
Bart Adams, Martin Wicke, Maks Ovsjanikov, Michael Wand,
Hans-Peter Seidel and Leonidas Guibas,

We present physically based algorithms for interactive deformable shape and motion modeling. We coarsely sample the objects with simulation nodes, and apply a meshless finite element method to obtain realistic deformations... [paper]

Computer Graphics Forum (CGF), 2010.
Robust Voronoi-based Curvature and Feature Estimation,
Quentin Mérigot, Maks Ovsjanikov and Leonidas Guibas

We present an efficient and robust method for extracting principal curvatures, sharp features and normal directions of a piecewise smooth surface from its point cloud sampling, with theoretical guarantees... [paper] [code]

Proc. SIAM/ACM, GD/SPM, 2009
(Best Paper Award)
ShapeGoogle: a computer vision approach for invariant shape retrieval,
Maks Ovsjanikov, Alexander Bronstein, Michael Bronstein and Leonidas Guibas

Feature-based methods have recently gained popularity in computer vision and pattern recognition communities. In this paper, we explore analogous approaches in the 3D world applied to the problem of non-rigid shape search and retrieval in large databases... [paper] [related code].

NORDIA Workshop, Proc. ICCV 2010
A Concise and Provably Informative Multi-scale Signature Based on Heat Diffusion,
Jian Sun, Maks Ovsjanikov and Leonidas Guibas

We propose a novel point signature based on the properties of the heat diffusion process on a shape. Our signature, called the Heat Kernel Signature (or HKS), is obtained by restricting the well-known heat kernel to the temporal... [paper]

Eurographics Symposium on Geometry Processing (SGP) 2009.
(Best Paper Award)
Efficient Reconstruction of Non-rigid Shape and Motion from Real-Time 3D Scanner Data,
Michael Wand, Bart Adams, Maks Ovsjanikov, Alexander Berner, Martin Bokeloh,
Philipp Jenke, Leonidas Guibas, Hans-Peter Seidel, Andreas Schilling

We present a new technique for reconstructing a single shape and its non-rigid motion from 3D scanning data. Our algorithm takes a set of time-varying sample points that show partial views of a deforming object... [paper]

ACM Transactions on Graphics (TOG) 2009.
Global Intrinsic Symmetries of Shapes,
Maks Ovsjanikov, Jian Sun and Leonidas Guibas

In this paper, we present a novel approach for efficiently computing symmetries of a shape which are invariant up to isometry preserving transformations. We show that the intrinsic symmetries are transformed into the Euclidean... [paper]

Computer Graphics Forum (Proc. SGP), 2008.
(Best Student Paper Award)
Meshless Modeling of Deformable Shapes and their Motion,
Bart Adams, Maks Ovsjanikov, Michael Wand, Hans-Peter Seidel and Leonidas J. Guibas

We present a new framework for interactive shape deformation modeling and key frame interpolation based on a meshless finite element formulation. We formulate rigidity and volume preservation constraints... [paper]

Proc. ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA), 2008.
Dynamic Geometry Registration,
Niloy J. Mitra, Simon Floery, Maks Ovsjanikov, Natasha Gelfand,
Leonidas Guibas and Helmut Pottmann

We propose an algorithm that performs registration of large sets of unstructured point clouds of moving and deforming objects without computing correspondences. Given as input a set of frames with dense spatial... [paper]

Proc. Eurographics Symposium on Geometry Processing (SGP), 2007.