Search Results for author:
Found 38 papers, 26 papers with code
Learning Continuous 3D Words for Text-to-Image Generation
We do this by engineering special sets of input tokens that can be transformed in a continuous manner -- we call them Continuous 3D Words.
Learning Subject-Aware Cropping by Outpainting Professional Photos
How to frame (or crop) a photo often depends on the image subject and its context; e. g., a human portrait.
VecFusion: Vector Font Generation with Diffusion
We present VecFusion, a new neural architecture that can generate vector fonts with varying topological structures and precise control point positions.
Segmentation-Based Parametric Painting
We introduce a novel image-to-painting method that facilitates the creation of large-scale, high-fidelity paintings with human-like quality and stylistic variation.
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.
DualVector: Unsupervised Vector Font Synthesis with Dual-Part Representation
Automatic generation of fonts can be an important aid to typeface design.
Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly
We instead propose to decompose shapes using a library of 3D parts provided by the user, giving full control over the choice of parts.
RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
In this paper, we present RenderDiffusion, the first diffusion model for 3D generation and inference, trained using only monocular 2D supervision.
Spotting Temporally Precise, Fine-Grained Events in Video
We introduce the task of spotting temporally precise, fine-grained events in video (detecting the precise moment in time events occur).
Ranked #6 on
Action Spotting
on SoccerNet-v2
APES: Articulated Part Extraction from Sprite Sheets
Rigged puppets are one of the most prevalent representations to create 2D character animations.
ASSET: Autoregressive Semantic Scene Editing with Transformers at High Resolutions
We present ASSET, a neural architecture for automatically modifying an input high-resolution image according to a user's edits on its semantic segmentation map.
Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency
Approaches for single-view reconstruction typically rely on viewpoint annotations, silhouettes, the absence of background, multiple views of the same instance, a template shape, or symmetry.
3D Object Reconstruction From A Single Image
3D Reconstruction
+2
Neural Strokes: Stylized Line Drawing of 3D Shapes
We show that, in contrast to previous image-based methods, the use of a geometric representation of 3D shape and 2D strokes allows the model to transfer important aspects of shape and texture style while preserving contours.
Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition
This leads to poor accuracy when downstream tasks, such as action recognition, depend on pose.
Font Completion and Manipulation by Cycling Between Multi-Modality Representations
The novel graph constructor maps a glyph's latent code to its graph representation that matches expert knowledge, which is trained to help the translation task.
GLASS: Geometric Latent Augmentation for Shape Spaces
We investigate the problem of training generative models on a very sparse collection of 3D models.
A Multi-Implicit Neural Representation for Fonts
Fonts are ubiquitous across documents and come in a variety of styles.
MarioNette: Self-Supervised Sprite Learning
Artists and video game designers often construct 2D animations using libraries of sprites -- textured patches of objects and characters.
CharacterGAN: Few-Shot Keypoint Character Animation and Reposing
Our model generates novel poses based on keypoint locations, which can be modified in real time while providing interactive feedback, allowing for intuitive reposing and animation.
DECOR-GAN: 3D Shape Detailization by Conditional Refinement
During testing, a style code is fed into the generator to condition the refinement.
LayoutGMN: Neural Graph Matching for Structural Layout Similarity
In particular, retrieval results by our network better match human judgement of structural layout similarity compared to both IoUs and other baselines including a state-of-the-art method based on graph neural networks and image convolution.
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.
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.
Modeling Artistic Workflows for Image Generation and Editing
People often create art by following an artistic workflow involving multiple stages that inform the overall design.
Improved Techniques for Training Single-Image GANs
Recently there has been an interest in the potential of learning generative models from a single image, as opposed to from a large dataset.
UprightNet: Geometry-Aware Camera Orientation Estimation from Single Images
We introduce UprightNet, a learning-based approach for estimating 2DoF camera orientation from a single RGB image of an indoor scene.
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.
BAE-NET: Branched Autoencoder for Shape Co-Segmentation
The unsupervised BAE-NET is trained with a collection of un-segmented shapes, using a shape reconstruction loss, without any ground-truth labels.
Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction
In this paper, we address the problem of 3D object mesh reconstruction from RGB videos.
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.
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
Multi-Content GAN for Few-Shot Font Style Transfer
In this work, we focus on the challenge of taking partial observations of highly-stylized text and generalizing the observations to generate unobserved glyphs in the ornamented typeface.
Opt: A Domain Specific Language for Non-linear Least Squares Optimization in Graphics and Imaging
Many graphics and vision problems can be expressed as non-linear least squares optimizations of objective functions over visual data, such as images and meshes.
3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
To amass training data for our model, we propose a self-supervised feature learning method that leverages the millions of correspondence labels found in existing RGB-D reconstructions.
Ranked #2 on
3D Reconstruction
on Scan2CAD
