Search Results for author:
Found 34 papers, 17 papers with code
Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension
Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.
Learning to Infer Generative Template Programs for Visual Concepts
We develop a learning paradigm that allows us to train networks that infer Template Programs directly from visual datasets that contain concept groupings.
R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding
We introduce the Reality-linked 3D Scenes (R3DS) dataset of synthetic 3D scenes mirroring the real-world scene arrangements from Matterport3D panoramas.
Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases
Unlike most prior work on indoor scene generation, our system does not require a large training dataset of existing 3D scenes.
Generalizing Single-View 3D Shape Retrieval to Occlusions and Unseen Objects
Single-view 3D shape retrieval is a challenging task that is increasingly important with the growth of available 3D data.
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.
Improving Unsupervised Visual Program Inference with Code Rewriting Families
Programs offer compactness and structure that makes them an attractive representation for visual data.
ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitives
The discovered abstractions capture common patterns (both structural and parametric) across the dataset, so that programs rewritten with these abstractions are more compact, and expose fewer degrees of freedom.
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.
CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Language
Recent works have demonstrated that natural language can be used to generate and edit 3D shapes.
ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model
Results show that our method can generate shapes consistent with text descriptions, and shapes evolve gradually as more phrases are added.
Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections
We operationalize this concept with an algorithm that optimizes a shape's part motion parameters such that it can transform into other shapes in the collection.
SHRED: 3D Shape Region Decomposition with Learned Local Operations
We present SHRED, a method for 3D SHape REgion Decomposition.
Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension
Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.
Ranked #1 on
Question Generation
on FairytaleQA
StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement
Despite its benefits for children's skill development and parent-child bonding, many parents do not often engage in interactive storytelling by having story-related dialogues with their child due to limited availability or challenges in coming up with appropriate questions.
Learning Body-Aware 3D Shape Generative Models
The body-shape-conditioned models produce chairs which will be comfortable for a person with the given body shape; the pose-conditioned models produce chairs which accommodate the given sitting pose.
Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms
We then discuss different strategies for solving the problem, and design two representative pipelines: one uses available 2D floor plans to guide selection and deformation of 3D rooms; the other learns to retrieve a set of compatible 3D rooms and combine them into novel layouts.
The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts
We present the Shape Part Slot Machine, a new method for assembling novel 3D shapes from existing parts by performing contact-based reasoning.
Learning to Infer Kinematic Hierarchies for Novel Object Instances
Manipulating an articulated object requires perceiving itskinematic hierarchy: its parts, how each can move, and howthose motions are coupled.
The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inference
We propose the Neurally-Guided Shape Parser (NGSP), a method that learns how to assign fine-grained semantic labels to regions of a 3D shape.
ShapeMOD: Macro Operation Discovery for 3D Shape Programs
In this paper, we present ShapeMOD, an algorithm for automatically discovering macros that are useful across large datasets of 3D shape programs.
Shape From Tracing: Towards Reconstructing 3D Object Geometry and SVBRDF Material from Images via Differentiable Path Tracing
In this paper, we explore how to use differentiable ray tracing to refine an initial coarse mesh and per-mesh-facet material representation.
PLAD: Learning to Infer Shape Programs with Pseudo-Labels and Approximate Distributions
Related to these approaches, we introduce a novel self-training variant unique to program inference, where program pseudo-labels are paired with their executed output shapes, avoiding label mismatch at the cost of an approximate shape distribution.
ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis
The program captures the subset of variability that is interpretable and editable.
GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation
Instead of executing translation directly, we steer the translation by requiring the network to produce in-between images that resemble weighted hybrids between images from the input domains.
Learning to Describe Scenes with Programs
We are able to understand the higher-level, abstract regularities within the scene such as symmetry and repetition.
Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models
We present a new, fast and flexible pipeline for indoor scene synthesis that is based on deep convolutional generative models.
Improving Shape Deformation in Unsupervised Image-to-Image Translation
Unsupervised image-to-image translation techniques are able to map local texture between two domains, but they are typically unsuccessful when the domains require larger shape change.
ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans
We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels.
An Improved Training Procedure for Neural Autoregressive Data Completion
In this paper, we provide evidence that the order-agnostic (OA) training procedure is suboptimal for data completion.
Learning to Infer Graphics Programs from Hand-Drawn Images
These drawing primitives are like a trace of the set of primitive commands issued by a graphics program.
Deep Amortized Inference for Probabilistic Programs
This paper proposes a system for amortized inference in PPLs.
Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks
Probabilistic inference algorithms such as Sequential Monte Carlo (SMC) provide powerful tools for constraining procedural models in computer graphics, but they require many samples to produce desirable results.
C3: Lightweight Incrementalized MCMC for Probabilistic Programs using Continuations and Callsite Caching
Lightweight, source-to-source transformation approaches to implementing MCMC for probabilistic programming languages are popular for their simplicity, support of existing deterministic code, and ability to execute on existing fast runtimes.
