Nissim Maruani

Contact | GitHub | Scholar | LinkedIn

I'm a third year PhD student at Inria, under the supervision of Pierre Alliez (Titane team) and Mathieu Desbrun (Geomerix team). Last summer, I interned at Adobe Research with mentorship from Yifan Wang. My work lies at the intersection of geometry processing and deep learning, focusing on differentiable geometric representations that enable fast and accurate reconstruction. I’m particularly interested in data-driven approaches and generative models.

Publications

Illustrator’s Depth: Monocular Layer Index Prediction for Image Decomposition
Nissim Maruani, Peiying Zhang, Siddhartha Chaudhuri, Matthew Fisher, Nanxuan Zhao, Vladimir G. Kim, Pierre Alliez, Mathieu Desbrun, Wang Yifan
We introduce Illustrator’s Depth, a novel definition of depth that addresses a key challenge in digital content creation: decomposing flat images into editable, ordered layers. Inspired by an artist’s compositional process, illustrator’s depth infers a layer index for each pixel, forming an interpretable image decomposition through a discrete, globally consistent ordering of elements optimized for editability. We also propose and train a neural network using a curated dataset of layered vector graphics to predict layering directly from raster inputs. Our layer index inference unlocks a range of powerful downstream applications. In particular, it significantly outperforms state-of-the-art baselines for image vectorization while also enabling high-fidelity text-to-vector-graphics generation, automatic 3D relief generation from 2D images, and intuitive depth-aware editing. By reframing depth from a physical quantity to a creative abstraction, illustrator's depth prediction offers a new foundation for editable image decomposition.
Arxiv, 2025

MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction
Antoine Guédon, Diego Gomez, Nissim Maruani, Bingchen Gong, George Drettakis, Maks Ovsjanikov
Our method introduces a novel differentiable mesh extraction framework that operates during the optimization of 3D Gaussian Splatting representations. At every training iteration, we differentiably extract a mesh—including both vertex locations and connectivity—only from Gaussian parameters. This enables gradient flow from the mesh to Gaussians, allowing us to promote bidirectional consistency between volumetric (Gaussians) and surface (extracted mesh) representations. This approach guides Gaussians toward configurations better suited for surface reconstruction, resulting in higher quality meshes with significantly fewer vertices. Our framework can be plugged into any Gaussian splatting representation, increasing performance while generating an order of magnitude fewer mesh vertices. MILo makes the reconstructions more practical for downstream applications like physics simulations and animation.
ACM Trans. Graph. (SIGGRAPH Asia - Journal Track), 2025

ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion
Nissim Maruani, Wang Yifan, Matthew Fisher, Pierre Alliez, Mathieu Desbrun
This paper proposes a new 3D generative model that learns to synthesize shape variations based on a single example. While generative methods for 3D objects have recently attracted much attention, current techniques often lack geometric details and/or require long training times and large resources. Our approach remedies these issues by combining sparse voxel grids and multiscale point, normal, and color sampling within an encoder-free neural architecture that can be trained efficiently and in parallel. We show that our resulting variations better capture the fine details of their original input and can capture more general types of surfaces than previous SDF-based methods. Moreover, we offer interactive generation of 3D shape variants, allowing more human control in the design loop if needed.
Proc. Conference on Computer Vision and Patter Recognition (CVPR), 2025

PoNQ: a Neural QEM-based Mesh Representation
Nissim Maruani, Maks Ovsjanikov, Pierre Alliez, Mathieu Desbrun
Although polygon meshes have been a standard representation in geometry processing, their irregular and combinatorial nature hinders their suitability for learning-based applications. In this work, we introduce a novel learnable mesh representation through a set of local 3D sample Points and their associated Normals and Quadric error metrics (QEM) w.r.t. the underlying shape, which we denote PoNQ. A global mesh is directly derived from PoNQ by efficiently leveraging the knowledge of the local quadric errors. Besides marking the first use of QEM within a neural shape representation, our contribution guarantees both topological and geometrical properties by ensuring that a PoNQ mesh does not self-intersect and is always the boundary of a volume. Notably, our representation does not rely on a regular grid, is supervised directly by the target surface alone, and also handles open surfaces with boundaries and/or sharp features. We demonstrate the efficacy of PoNQ through a learning-based mesh prediction from SDF grids and show that our method surpasses recent state-of-the-art techniques in terms of both surface and edge-based metrics.
Proc. Conference on Computer Vision and Patter Recognition (CVPR), 2024

VoroMesh: Learning Watertight Surface Meshes with Voronoi Diagrams
Nissim Maruani, Roman Klokov, Maks Ovsjanikov, Pierre Alliez, Mathieu Desbrun
In stark contrast to the case of images, finding a concise, learnable discrete representation of 3D surfaces remains a challenge. In particular, while polygon meshes are arguably the most common surface representation used in geometry processing, their irregular and combinatorial structure often make them unsuitable for learning-based applications. In this work, we present VoroMesh, a novel and differentiable Voronoi-based representation of water- tight 3D shape surfaces. From a set of 3D points (called generators) and their associated occupancy, we define our boundary representation through the Voronoi diagram of the generators as the subset of Voronoi faces whose two associated (equidistant) generators are of opposite occupancy: the resulting polygon mesh forms a watertight approximation of the target shape’s boundary. To learn the position of the generators, we propose a novel loss function, dubbed VoroLoss, that minimizes the distance from groundtruth surface samples to the closest faces of the Voronoi diagram which does not require an explicit construction of the entire Voronoi diagram. A direct optimization of the Voroloss to obtain generators on the Thingi32 dataset demonstrates the geometric efficiency of our representation compared to axiomatic meshing algorithms and recent learning-based mesh representations. We further use VoroMesh in a learning-based mesh prediction task from input SDF grids on the ABC dataset, and show comparable performance to state-of-the-art methods while guaranteeing closed output surfaces free of self-intersections.
Proc. International Conference on Computer Vision (ICCV), 2023

Feature-Preserving Offset Mesh Generation from Topology-Adapted Octrees
Daniel Zint, Nissim Maruani, Mael Rouxel-Labbé, Pierre Alliez
We introduce a reliable method to generate offset meshes from input triangle meshes or triangle soups. Our method proceeds in two steps. The first step performs a Dual Contouring method on the offset surface, operating on an adaptive octree that is refined in areas where the offset topology is complex. Our approach substantially reduces memory consumption and runtime compared to isosurfacing methods operating on uniform grids. The second step improves the output Dual Contouring mesh with an offset-aware remeshing algorithm to reduce the normal deviation between the mesh facets and the exact offset. This remeshing process reconstructs concave sharp features and approximates smooth shapes in convex areas up to a user-defined precision. We show the effectiveness and versatility of our method by applying it to a wide range of input meshes. We also benchmark our method on the entire Thingi10k dataset: watertight, 2-manifold offset meshes are obtained for 100% of the cases.
Symposium on geometry processing (SGP), 2023

Teaching

• ENS-PSL (2022-Today, Paris, France): exploring new ways of teaching maths with MathAData
• Polytech Nice (November 2025): Lecture & practical session on 3D Shape Learning within the Deep Learning class
• La Rotonde (2018-2019, Saint-Étienne, France): Science Mediation at La main à la pâte

Talks

• Stanford, Geometric Computation group, July 2024
• 3IA Côte d'Azur, June 2023, November 2025

Reviewer

• Computers & Graphics 2026, EUROGRAPHICS 2026, BMVC 2025, SIGGRAPH 2025, BMVC 2024, SIGGRAPH ASIA 2024, SIGGRAPH 2024, BMVC 2023

Education

• ENS Paris-Saclay (2021-2022, Gif-sur-Yvette, France): Master MVA
• École polytechnique (2018-2022, Saclay, France): Engineering Curriculum
• Lycée Louis-le-Grand (2016-2018, Paris, France): "Classe prépa"

Coding projects

Laser Simulation

Forgery Detection

VSA

Image Segmentation

Plenoxels

Autoregressive Diffusion

Analog Grain Simulation

Paper Plane Simulation