Search Results for author:
Found 20 papers, 7 papers with code
VLMaterial: Procedural Material Generation with Large Vision-Language Models
Procedural materials, represented as functional node graphs, are ubiquitous in computer graphics for photorealistic material appearance design.
CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
We present CAT4D, a method for creating 4D (dynamic 3D) scenes from monocular video.
Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis
Accurate reconstruction of complex dynamic scenes from just a single viewpoint continues to be a challenging task in computer vision.
PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation
Unlike unconditional or text-conditioned dynamics generation, action-conditioned dynamics requires perceiving the physical material properties of objects and grounding the 3D motion prediction on these properties, such as object stiffness.
Neural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulation
To tackle the problem of efficiently editing neural implicit fields, we introduce Neural Impostor, a hybrid representation incorporating an explicit tetrahedral mesh alongside a multigrid implicit field designated for each tetrahedron within the explicit mesh.
Textureless Deformable Surface Reconstruction with Invisible Markers
Leveraging the markers, we design a multi-camera system that captures surface deformation under the UV light and the visible light in a time multiplexing fashion.
Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
Specifically, we encode the input 3D textured shape into triplane feature maps that represent the signed distance and texture fields of the input.
Implicit Neural Spatial Representations for Time-dependent PDEs
Whereas classical solvers can dynamically adapt their spatial representation only by resorting to complex remeshing algorithms, our INSR approach is intrinsically adaptive.
Learning to Generate 3D Shapes from a Single Example
Existing generative models for 3D shapes are typically trained on a large 3D dataset, often of a specific object category.
Can one hear the shape of a neural network?: Snooping the GPU via Magnetic Side Channel
We find that each layer component's evaluation produces an identifiable magnetic signal signature, from which layer topology, width, function type, and sequence order can be inferred using a suitably trained classifier and a joint consistency optimization based on integer programming.
DeepCAD: A Deep Generative Network for Computer-Aided Design Models
We present the first 3D generative model for a drastically different shape representation --- describing a shape as a sequence of computer-aided design (CAD) operations.
Ranked #3 on
CAD Reconstruction
on CC3D
(Chamfer Distance (median) metric)
Linear Semantics in Generative Adversarial Networks
Given a trained GAN and as few as eight semantic annotations, the user is able to generate diverse images subject to a user-provided semantic layout, and control the synthesized image semantics.
One Man's Trash is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examples
To defend against adversarial examples, a plausible idea is to obfuscate the network's gradient with respect to the input image.
Enhancing Adversarial Defense by k-Winners-Take-All
In all cases, the robustness of k-WTA networks outperforms that of traditional networks under white-box attacks.
Rethinking Generative Mode Coverage: A Pointwise Guaranteed Approach
The conventional wisdom to this end is by reducing through training a statistical distance (such as $f$-divergence) between the generated distribution and provided data distribution.
BourGAN: Generative Networks with Metric Embeddings
This paper addresses the mode collapse for generative adversarial networks (GANs).
Scene-Aware Audio for 360\textdegree{} Videos
In our validations, we show that our synthesized spatial audio matches closely with recordings using ambisonic microphones.
FontCode: Embedding Information in Text Documents using Glyph Perturbation
We then introduce an algorithm that embeds a user-provided message in the text document and produces an encoded document whose appearance is minimally perturbed from the original document.
AirCode: Unobtrusive Physical Tags for Digital Fabrication
We present AirCode, a technique that allows the user to tag physically fabricated objects with given information.
