Search Results for author:
Found 46 papers, 22 papers with code
Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects
We propose a generative technique to edit 3D shapes, represented as meshes, NeRFs, or Gaussian Splats, in approximately 3 seconds, without the need for running an SDS type of optimization.
SAMa: Material-aware 3D Selection and Segmentation
Our approach works on arbitrary 3D representations and outperforms several strong baselines in terms of selection accuracy and multiview consistency.
DECOLLAGE: 3D Detailization by Controllable, Localized, and Learned Geometry Enhancement
Given a coarse voxel shape (e. g., one produced with a simple box extrusion tool or via generative modeling), a user can directly "paint" desired target styles representing compelling geometric details, from input exemplar shapes, over different regions of the coarse shape.
MeshUp: Multi-Target Mesh Deformation via Blended Score Distillation
We propose MeshUp, a technique that deforms a 3D mesh towards multiple target concepts, and intuitively controls the region where each concept is expressed.
Text-guided Controllable Mesh Refinement for Interactive 3D Modeling
First, we generate a single-view RGB image conditioned on the input coarse geometry and the input text prompt.
One Noise to Rule Them All: Learning a Unified Model of Spatially-Varying Noise Patterns
Procedural noise is a fundamental component of computer graphics pipelines, offering a flexible way to generate textures that exhibit "natural" random variation.
GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis
We introduce GEM3D -- a new deep, topology-aware generative model of 3D shapes.
As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors
To better preserve the identity of the edited mesh, we fine-tune our 2D diffusion model with LoRA.
Explorable Mesh Deformation Subspaces from Unstructured Generative Models
Deep generative models of 3D shapes often feature continuous latent spaces that can, in principle, be used to explore potential variations starting from a set of input shapes.
Neural Semantic Surface Maps
We present an automated technique for computing a map between two genus-zero shapes, which matches semantically corresponding regions to one another.
Neural Progressive Meshes
The recent proliferation of 3D content that can be consumed on hand-held devices necessitates efficient tools for transmitting large geometric data, e. g., 3D meshes, over the Internet.
TextDeformer: Geometry Manipulation using Text Guidance
Our key observation is that Jacobians are a representation that favors smoother, large deformations, leading to a global relation between vertices and pixels, and avoiding localized noisy gradients.
DA Wand: Distortion-Aware Selection using Neural Mesh Parameterization
We present a neural technique for learning to select a local sub-region around a point which can be used for mesh parameterization.
Self-Supervised Representation Learning for CAD
Assisting design with data-driven machine learning methods is hampered by lack of labeled data in CAD's native format; the parametric boundary representation (B-Rep).
PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation
Our key insight is to copy and deform patches from the partial input to complete missing regions.
Learning Joint Surface Atlases
We demonstrate that this improves the quality of the learned surface representation, as well as its consistency in a collection of related shapes.
Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes
This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network, enabling training and evaluating over heterogeneous collections of meshes that do not share a triangulation, as well as producing highly detail-preserving maps whose accuracy exceeds current state of the art.
Neural Convolutional Surfaces
Our pipeline and architecture are designed so that disentanglement of global geometry from local details is accomplished through optimization, in a completely unsupervised manner.
Learning Proximal Operators to Discover Multiple Optima
We present an end-to-end method to learn the proximal operator of a family of training problems so that multiple local minima can be quickly obtained from initial guesses by iterating the learned operator, emulating the proximal-point algorithm that has fast convergence.
Möbius Convolutions for Spherical CNNs
M\"obius transformations play an important role in both geometry and spherical image processing - they are the group of conformal automorphisms of 2D surfaces and the spherical equivalent of homographies.
Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases
The key to making these correspondences semantically meaningful is to guarantee that the metric tensors computed at corresponding points are as similar as possible.
Ranked #1 on
Surface Reconstruction
on ANIM
AutoMate: A Dataset and Learning Approach for Automatic Mating of CAD Assemblies
To train our system, we compiled the first large scale dataset of BREP CAD assemblies, which we are releasing along with benchmark mate prediction tasks.
Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases
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.
Field Convolutions for Surface CNNs
We present a novel surface convolution operator acting on vector fields that is based on a simple observation: instead of combining neighboring features with respect to a single coordinate parameterization defined at a given point, we have every neighbor describe the position of the point within its own coordinate frame.
Joint Learning of 3D Shape Retrieval and Deformation
In fact, we use the embedding space to guide the shape pairs used to train the deformation module, so that it invests its capacity in learning deformations between meaningful shape pairs.
DECOR-GAN: 3D Shape Detailization by Conditional Refinement
During testing, a style code is fed into the generator to condition the refinement.
COALESCE: Component Assembly by Learning to Synthesize Connections
We introduce COALESCE, the first data-driven framework for component-based shape assembly which employs deep learning to synthesize part connections.
Self-supervised Learning of Point Clouds via Orientation Estimation
A point cloud can be rotated in infinitely many ways, which provides a rich label-free source for self-supervision.
Ranked #11 on
3D Point Cloud Linear Classification
on ModelNet40
3D Point Cloud Linear Classification
Self-Supervised Learning
+1
Coupling Explicit and Implicit Surface Representations for Generative 3D Modeling
We propose a novel neural architecture for representing 3D surfaces, which harnesses two complementary shape representations: (i) an explicit representation via an atlas, i. e., embeddings of 2D domains into 3D; (ii) an implicit-function representation, i. e., a scalar function over the 3D volume, with its levels denoting surfaces.
Neural Subdivision
During inference, our method takes a coarse triangle mesh as input and recursively subdivides it to a finer geometry by applying the fixed topological updates of Loop Subdivision, but predicting vertex positions using a neural network conditioned on the local geometry of a patch.
Affinity Graph Supervision for Visual Recognition
Affinity graphs are widely used in deep architectures, including graph convolutional neural networks and attention networks.
Neural Cages for Detail-Preserving 3D Deformations
The goal of our method is to warp a source shape to match the general structure of a target shape, while preserving the surface details of the source.
Neural Puppet: Generative Layered Cartoon Characters
We capture these subtle changes by applying an image translation network to refine the mesh rendering, providing an end-to-end model to generate new animations of a character with high visual quality.
Learning elementary structures for 3D shape generation and matching
We propose to represent shapes as the deformation and combination of learnable elementary 3D structures, which are primitives resulting from training over a collection of shape.
Ranked #8 on
3D Dense Shape Correspondence
on SHREC'19
(using extra training data)
Unsupervised cycle-consistent deformation for shape matching
We propose a self-supervised approach to deep surface deformation.
Deep Parametric Shape Predictions using Distance Fields
Many tasks in graphics and vision demand machinery for converting shapes into consistent representations with sparse sets of parameters; these representations facilitate rendering, editing, and storage.
Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction
In this paper, we address the problem of 3D object mesh reconstruction from RGB videos.
Learning Material-Aware Local Descriptors for 3D Shapes
Unfortunately, only a small fraction of shapes in 3D repositories are labeled with physical mate- rials, posing a challenge for learning methods.
3D-CODED: 3D Correspondences by Deep Deformation
By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template.
Learning Fuzzy Set Representations of Partial Shapes on Dual Embedding Spaces
Modeling relations between components of 3D objects is essential for many geometry editing tasks.
Graphics I.3.5
3D-CODED : 3D Correspondences by Deep Deformation
By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template.
Ranked #9 on
3D Dense Shape Correspondence
on SHREC'19
(using extra training data)
A Papier-Mâché Approach to Learning 3D Surface Generation
We introduce a method for learning to generate the surface of 3D shapes.
AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation
We introduce a method for learning to generate the surface of 3D shapes.
Ranked #5 on
Point Cloud Completion
on Completion3D
Tags2Parts: Discovering Semantic Regions from Shape Tags
We test our method on segmentation benchmarks and show that even with weak supervision of whole shape tags, our method can infer meaningful semantic regions, without ever observing shape segmentations.
ComplementMe: Weakly-Supervised Component Suggestions for 3D Modeling
The combinatorial nature of part arrangements poses another challenge, since the retrieval network is not a function: several complements can be appropriate for the same input.
Graphics I.3.5
Learning Local Shape Descriptors from Part Correspondences With Multi-view Convolutional Networks
We present a new local descriptor for 3D shapes, directly applicable to a wide range of shape analysis problems such as point correspondences, semantic segmentation, affordance prediction, and shape-to-scan matching.
