Search Results for author:
Found 25 papers, 10 papers with code
StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows
We evaluate our method using the face and the car latent space of StyleGAN, and demonstrate fine-grained disentangled edits along various attributes on both real photographs and StyleGAN generated images.
StructureNet: Hierarchical Graph Networks for 3D Shape Generation
We introduce StructureNet, a hierarchical graph network which (i) can directly encode shapes represented as such n-ary graphs; (ii) can be robustly trained on large and complex shape families; and (iii) can be used to generate a great diversity of realistic structured shape geometries.
Differentiable Surface Triangulation
Our method builds on the result that any 2D triangulation can be achieved by a suitably perturbed weighted Delaunay triangulation.
Labels4Free: Unsupervised Segmentation using StyleGAN
We propose an unsupervised segmentation framework for StyleGAN generated objects.
Learning Delaunay Surface Elements for Mesh Reconstruction
We leverage the properties of 2D Delaunay triangulations to construct a mesh from manifold surface elements.
BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
Our experiments show that using explicit 3D features to represent objects allows BlockGAN to learn disentangled representations both in terms of objects (foreground and background) and their properties (pose and identity).
Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images
We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views.
StructEdit: Learning Structural Shape Variations
Learning to encode differences in the geometry and (topological) structure of the shapes of ordinary objects is key to generating semantically plausible variations of a given shape, transferring edits from one shape to another, and many other applications in 3D content creation.
RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects.
GLASS: Geometric Latent Augmentation for Shape Spaces
We investigate the problem of training generative models on a very sparse collection of 3D models.
Unsupervised Intuitive Physics from Visual Observations
While learning models of intuitive physics is an increasingly active area of research, current approaches still fall short of natural intelligences in one important regard: they require external supervision, such as explicit access to physical states, at training and sometimes even at test times.
Facade Segmentation in the Wild
Specifically, we propose a MULTIFACSEGNET architecture to assign multiple labels to each pixel, a SEPARABLE architecture as a low-rank formulation that encourages extraction of rectangular elements, and a COMPATIBILITY network that simultaneously seeks segmentation across facade element types allowing the network to 'see' intermediate output probabilities of the various facade element classes.
Taking Visual Motion Prediction To New Heightfields
In order to be able to leverage the approximation capabilities of artificial intelligence techniques in such physics related contexts, researchers have handcrafted the relevant states, and then used neural networks to learn the state transitions using simulation runs as training data.
SeeThrough: Finding Chairs in Heavily Occluded Indoor Scene Images
Discovering 3D arrangements of objects from single indoor images is important given its many applications including interior design, content creation, etc.
Learning to Represent Mechanics via Long-term Extrapolation and Interpolation
While the basic laws of Newtonian mechanics are well understood, explaining a physical scenario still requires manually modeling the problem with suitable equations and associated parameters.
ImageSpirit: Verbal Guided Image Parsing
This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images.
How does Lipschitz Regularization Influence GAN Training?
In this work, we uncover an even more important effect of Lipschitz regularization by examining its impact on the loss function: It degenerates GAN loss functions to almost linear ones by restricting their domain and interval of attainable gradient values.
Escaping Plato's Cave: 3D Shape From Adversarial Rendering
We can successfully reconstruct 3D shapes from unstructured 2D images and extensively evaluate PlatonicGAN on a range of synthetic and real data sets achieving consistent improvements over baseline methods.
Object Properties Inferring from and Transfer for Human Interaction Motions
In this paper, we present a fine-grained action recognition method that learns to infer such latent object properties from human interaction motion alone.
Walk2Map: Extracting Floor Plans from Indoor Walk Trajectories
Thanks to recent advances in data-driven inertial odometry, such minimalistic input data can be acquired from the IMU readings of consumer-level smartphones, which allows for an effortless and scalable mapping of real-world indoor spaces.
SketchGen: Generating Constrained CAD Sketches
Sketches can be represented as graphs, with the primitives as nodes and the constraints as edges.
COFS: Controllable Furniture layout Synthesis
Scalable generation of furniture layouts is essential for many applications in virtual reality, augmented reality, game development and synthetic data generation.
3inGAN: Learning a 3D Generative Model from Images of a Self-similar Scene
We introduce 3inGAN, an unconditional 3D generative model trained from 2D images of a single self-similar 3D scene.
HoloDiffusion: Training a 3D Diffusion Model using 2D Images
We show that our diffusion models are scalable, train robustly, and are competitive in terms of sample quality and fidelity to existing approaches for 3D generative modeling.
Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D
Our key insight is to lift diffusion activations for an object to 3D using a proxy depth, 3D-transform the depth and associated activations, and project them back to image space.
