Search Results for author:
Found 24 papers, 14 papers with code
Neural Control Variates with Automatic Integration
This paper proposes a novel approach to construct learnable parametric control variates functions from arbitrary neural network architectures.
Robust Symmetry Detection via Riemannian Langevin Dynamics
In contrast, learning-based methods may be more robust to noise, but often overlook partial symmetries due to the scarcity of annotated data.
DiffusionPDE: Generative PDE-Solving Under Partial Observation
We introduce a general framework for solving partial differential equations (PDEs) using generative diffusion models.
MegaScenes: Scene-Level View Synthesis at Scale
Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications.
InfoGaussian: Structure-Aware Dynamic Gaussians through Lightweight Information Shaping
In particular, it can be challenging to animate and move objects in the scene, which requires coordination among many Gaussians.
BlenderAlchemy: Editing 3D Graphics with Vision-Language Models
Specifically, we design a vision-based edit generator and state evaluator to work together to find the correct sequence of actions to achieve the goal.
PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
This marks a significant advancement towards modeling photorealistic digital humans using physically based inverse rendering with physics in the loop.
GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation
These metrics lack the flexibility to generalize to different evaluation criteria and might not align well with human preferences.
Accurate Differential Operators for Hybrid Neural Fields
Yet in many applications like rendering and simulation, hybrid neural fields can cause noticeable and unreasonable artifacts.
Orthogonal Adaptation for Modular Customization of Diffusion Models
In this paper, we address a new problem called Modular Customization, with the goal of efficiently merging customized models that were fine-tuned independently for individual concepts.
NeRF Revisited: Fixing Quadrature Instability in Volume Rendering
Volume rendering requires evaluating an integral along each ray, which is numerically approximated with a finite sum that corresponds to the exact integral along the ray under piecewise constant volume density.
Learning a Diffusion Prior for NeRFs
Neural Radiance Fields (NeRFs) have emerged as a powerful neural 3D representation for objects and scenes derived from 2D data.
Polynomial Neural Fields for Subband Decomposition and Manipulation
We use this framework to design Fourier PNFs, which match state-of-the-art performance in signal representation tasks that use neural fields.
Residual Aligned: Gradient Optimization for Non-Negative Image Synthesis
In this work, we address an important problem of optical see through (OST) augmented reality: non-negative image synthesis.
Stay Positive: Non-Negative Image Synthesis for Augmented Reality
In applications such as optical see-through and projector augmented reality, producing images amounts to solving non-negative image generation, where one can only add light to an existing image.
Geometry Processing with Neural Fields
Most existing geometry processing algorithms use meshes as the default shape representation.
Learning Gradient Fields for Shape Generation
Point cloud generation thus amounts to moving randomly sampled points to high-density areas.
QPyTorch: A Low-Precision Arithmetic Simulation Framework
Low-precision training reduces computational cost and produces efficient models.
PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes and the second level is the distribution of points given a shape.
Ranked #4 on
Point Cloud Generation
on ShapeNet Car
SWALP : Stochastic Weight Averaging in Low-Precision Training
Low precision operations can provide scalability, memory savings, portability, and energy efficiency.
Deep Fundamental Matrix Estimation without Correspondences
Estimating fundamental matrices is a classic problem in computer vision.
Learning Single-View 3D Reconstruction with Limited Pose Supervision
It is expensive to label images with 3D structure or precise camera pose.
Learning to Evaluate Image Captioning
To address these two challenges, we propose a novel learning based discriminative evaluation metric that is directly trained to distinguish between human and machine-generated captions.
Fast Reading Comprehension with ConvNets
State-of-the-art deep reading comprehension models are dominated by recurrent neural nets.
