Search Results for author:
Found 87 papers, 42 papers with code
Feature Augmentation via Nonparametrics and Selection (FANS) in High Dimensional Classification
We motivate FANS by generalizing the Naive Bayes model, writing the log ratio of joint densities as a linear combination of those of marginal densities.
Neyman-Pearson Classification under High-Dimensional Settings
Most existing binary classification methods target on the optimization of the overall classification risk and may fail to serve some real-world applications such as cancer diagnosis, where users are more concerned with the risk of misclassifying one specific class than the other.
Mesh Denoising via Cascaded Normal Regression
At runtime, our method applies the learned cascaded regression functions to a noisy input mesh and reconstructs the denoised mesh from the output facet normals.
Demography-based Facial Retouching Detection using Subclass Supervised Sparse Autoencoder
However, previous work on this topic has not considered whether or how accuracy of retouching detection varies with the demography of face images.
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis.
Ranked #4 on
3D Object Classification
on ModelNet40
Intentional Control of Type I Error over Unconscious Data Distortion: a Neyman-Pearson Approach to Text Classification
To deal with inestimable data distortion, we propose the use of the Neyman-Pearson (NP) classification paradigm, which minimizes type II error under a user-specified type I error constraint.
Neyman-Pearson classification: parametrics and sample size requirement
In this work, we employ the parametric linear discriminant analysis (LDA) model and propose a new parametric thresholding algorithm, which does not need the minimum sample size requirements on class $0$ observations and thus is suitable for small sample applications such as rare disease diagnosis.
View-volume Network for Semantic Scene Completion from a Single Depth Image
We introduce a View-Volume convolutional neural network (VVNet) for inferring the occupancy and semantic labels of a volumetric 3D scene from a single depth image.
Ranked #20 on
3D Semantic Scene Completion
on NYUv2
PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames
Surface meshes are widely used shape representations and capture finer geometry data than point clouds or volumetric grids, but are challenging to apply CNNs directly due to their non-Euclidean structure.
Ranked #27 on
Semantic Segmentation
on ScanNet
Deep Single-View 3D Object Reconstruction with Visual Hull Embedding
The key idea of our method is to leverage object mask and pose estimation from CNNs to assist the 3D shape learning by constructing a probabilistic single-view visual hull inside of the network.
Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes
The Adaptive O-CNN encoder takes the planar patch normal and displacement as input and performs 3D convolutions only at the octants at each level, while the Adaptive O-CNN decoder infers the shape occupancy and subdivision status of octants at each level and estimates the best plane normal and displacement for each leaf octant.
Image Smoothing via Unsupervised Learning
Image smoothing represents a fundamental component of many disparate computer vision and graphics applications.
Learn a Prior for RHEA for Better Online Planning
In this paper, we propose to learn a prior for RHEA in an offline manner by training a value network and a policy network.
A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images
To this end, we propose in this paper a skeleton-bridged, stage-wise learning approach to address the challenge.
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency. However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth 3D face shapes are scarce.
Ranked #3 on
3D Face Reconstruction
on Florence
(RMSE Cooperative metric)
A Skeleton-bridged Deep Learning Approach for Generating Meshesof Complex Topologies from Single RGB Image
To this end, we propose in this paper a skeleton-bridged, stage-wise learning approach to address the challenge.
Synthesizing 3D Shapes from Silhouette Image Collections using Multi-projection Generative Adversarial Networks
Key to our method is a novel multi-projection generative adversarial network (MP-GAN) that trains a 3D shape generator to be consistent with multiple 2D projections of the 3D shapes, and without direct access to these 3D shapes.
Imbalanced classification: a paradigm-based review
For each pair of resampling techniques and classification methods, we use simulation studies and a real data set on credit card fraud to study the performance under different evaluation metrics.
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
Our method can also be used to embed real images into the disentangled latent space.
Deep 3D Portrait from a Single Image
We evaluate the accuracy of our method both in 3D and with pose manipulation tasks on 2D images.
Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completion
Acquiring complete and clean 3D shape and scene data is challenging due to geometric occlusion and insufficient views during 3D capturing.
A Closer Look at Local Aggregation Operators in Point Cloud Analysis
Our investigation reveals that despite the different designs of these operators, all of these operators make surprisingly similar contributions to the network performance under the same network input and feature numbers and result in the state-of-the-art accuracy on standard benchmarks.
Ranked #4 on
3D Semantic Segmentation
on PartNet
Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination
Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learning methods still cannot offer a generic network for various shape analysis tasks with competitive performance to supervised methods.
Ranked #2 on
3D Semantic Segmentation
on PartNet
3D Point Cloud Linear Classification
3D Semantic Segmentation
Object-based Illumination Estimation with Rendering-aware Neural Networks
With the estimated lighting, virtual objects can be rendered in AR scenarios with shading that is consistent to the real scene, leading to improved realism.
SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images
However, they all have their own drawbacks, and cannot properly reconstruct the surface shapes of complex topologies, arguably due to a lack of constraints on the topologicalstructures in their learning frameworks.
Field-Tuned Quantum Effects in a Triangular-Lattice Ising Magnet
We report thermodynamic and neutron scattering measurements of the triangular-lattice quantum Ising magnet TmMgGaO 4 in longitudinal magnetic fields.
Strongly Correlated Electrons Materials Science
Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence
We propose a novel Deformed Implicit Field (DIF) representation for modeling 3D shapes of a category and generating dense correspondences among shapes.
Bridging Cost-sensitive and Neyman-Pearson Paradigms for Asymmetric Binary Classification
In contrast, the Neyman-Pearson paradigm can train classifiers to achieve a high-probability control of the population type I error, but it relies on sample splitting that reduces the effective training sample size.
Learning High-Fidelity Face Texture Completion Without Complete Face Texture
For face texture completion, previous methods typically use some complete textures captured by multiview imaging systems or 3D scanners for supervised learning.
Deep Implicit Moving Least-Squares Functions for 3D Reconstruction
We incorporate IMLS surface generation into deep neural networks for inheriting both the flexibility of point sets and the high quality of implicit surfaces.
Group-Free 3D Object Detection via Transformers
Instead of grouping local points to each object candidate, our method computes the feature of an object from all the points in the point cloud with the help of an attention mechanism in the Transformers \cite{vaswani2017attention}, where the contribution of each point is automatically learned in the network training.
Ranked #3 on
3D Object Detection
on SUN-RGBD
High-Resolution Optical Flow from 1D Attention and Correlation
Optical flow is inherently a 2D search problem, and thus the computational complexity grows quadratically with respect to the search window, making large displacements matching infeasible for high-resolution images.
Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent
Finding diverse and representative Pareto solutions from the Pareto front is a key challenge in multi-objective optimization (MOO).
Sampling with Trusthworthy Constraints: A Variational Gradient Framework
In this work, we propose a family of constrained sampling algorithms which generalize Langevin Dynamics (LD) and Stein Variational Gradient Descent (SVGD) to incorporate a moment constraint specified by a general nonlinear function.
Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields
Multilayer perceptrons (MLPs) have been successfully used to represent 3D shapes implicitly and compactly, by mapping 3D coordinates to the corresponding signed distance values or occupancy values.
StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation
Our framework, dubbed StyleCariGAN, automatically creates a realistic and detailed caricature from an input photo with optional controls on shape exaggeration degree and color stylization type.
Indoor Scene Generation from a Collection of Semantic-Segmented Depth Images
Different from existing methods that represent an indoor scene with the type, location, and other properties of objects in the room and learn the scene layout from a collection of complete 3D indoor scenes, our method models each indoor scene as a 3D semantic scene volume and learns a volumetric generative adversarial network (GAN) from a collection of 2. 5D partial observations of 3D scenes.
Joint Multi-User Communication and Sensing Exploiting Both Signal and Environment Sparsity
As a potential technology feature for 6G wireless networks, the idea of sensing-communication integration requires the system not only to complete reliable multi-user communication but also to achieve accurate environment sensing.
Sampling with Trusthworthy Constraints: A Variational Gradient Framework
In this work, we propose a family of constrained sampling algorithms which generalize Langevin Dynamics (LD) and Stein Variational Gradient Descent (SVGD) to incorporate a moment constraint specified by a general nonlinear function.
Asymmetric error control under imperfect supervision: a label-noise-adjusted Neyman-Pearson umbrella algorithm
It is somewhat surprising that even when common NP classifiers ignore the label noise in the training stage, they are still able to control the type I error with high probability.
Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent
Finding diverse and representative Pareto solutions from the Pareto front is a key challenge in multi-objective optimization (MOO).
VirtualCube: An Immersive 3D Video Communication System
The VirtualCube system is a 3D video conference system that attempts to overcome some limitations of conventional technologies.
GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation
3D-aware image generative modeling aims to generate 3D-consistent images with explicitly controllable camera poses.
Transformer Based Line Segment Classifier With Image Context for Real-Time Vanishing Point Detection in Manhattan World
To achieve this goal, we propose a novel Transformer based Line segment Classifier (TLC) that can group line segments in images and estimate the corresponding vanishing points.
MPS-NeRF: Generalizable 3D Human Rendering from Multiview Images
For this task, we propose a simple yet effective method to train a generalizable NeRF with multiview images as conditional input.
Semi-supervised 3D shape segmentation with multilevel consistency and part substitution
We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and a large amount of unlabeled 3D data.
Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations
Our method encodes the volumetric field of a 3D shape with an adaptive feature volume organized by an octree and applies a compact multilayer perceptron network for mapping the features to the field value at each 3D position.
What are People Talking about in #BlackLivesMatter and #StopAsianHate? Exploring and Categorizing Twitter Topics Emerging in Online Social Movements through the Latent Dirichlet Allocation Model
Minority groups have been using social media to organize social movements that create profound social impacts.
ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation
We view the reconstruction of CAD models in the boundary representation (B-Rep) as the detection of geometric primitives of different orders, i. e. vertices, edges and surface patches, and the correspondence of primitives, which are holistically modeled as a chain complex, and show that by modeling such comprehensive structures more complete and regularized reconstructions can be achieved.
GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds
This paper proposes a novel 3D-aware GAN that can generate high resolution images (up to 1024X1024) while keeping strict 3D consistency as in volume rendering.
SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation
We further complement the evaluation metrics of 3D generative models with the shading-image-based Fr\'echet inception distance (FID) scores to better assess visual quality and shape distribution of the generated shapes.
Environment Sensing Considering the Occlusion Effect: A Multi-View Approach
In this paper, we consider the problem of sensing the environment within a wireless cellular framework.
Sparse Ellipsometry: Portable Acquisition of Polarimetric SVBRDF and Shape with Unstructured Flash Photography
Ellipsometry techniques allow to measure polarization information of materials, requiring precise rotations of optical components with different configurations of lights and sensors.
Deep Deformable 3D Caricatures with Learned Shape Control
To achieve the goal, we propose an MLP-based framework for building a deformable surface model, which takes a latent code and produces a 3D surface.
Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation
Our method exploits semantic segmentation to fuse nonlocal instance features, such as center prediction, and further enhances the fusion scheme in a multi- and cross-level way.
Ranked #1 on
3D Instance Segmentation
on PartNet
Generative Deformable Radiance Fields for Disentangled Image Synthesis of Topology-Varying Objects
Experiments show that our method can successfully learn the generative model from unstructured monocular images and well disentangle the shape and appearance for objects (e. g., chairs) with large topological variance.
Hierarchical Neyman-Pearson Classification for Prioritizing Severe Disease Categories in COVID-19 Patient Data
Here, we propose a hierarchical NP (H-NP) framework and an umbrella algorithm that generally adapts to popular classification methods and controls the under-classification errors with high probability.
AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars
To achieve meaningful control over facial expressions via deformation, we propose a 3D-level imitative learning scheme between the generator and a parametric 3D face model during adversarial training of the 3D-aware GAN.
NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-shot Real Image Animation
Furthermore, our method leverages explicit and implicit 3D regularizations using the in-domain neighborhood samples around the optimized latent code to remove geometrical and visual artifacts.
RemoteTouch: Enhancing Immersive 3D Video Communication with Hand Touch
A key challenge in emulating the remote hand touch is the realistic rendering of the participant's hand and arm as the hand touches the screen.
ReBotNet: Fast Real-time Video Enhancement
The first branch learns spatio-temporal features by tokenizing the input frames along the spatial and temporal dimensions using a ConvNext-based encoder and processing these abstract tokens using a bottleneck mixer.
Synergistic Potential Functions from Single Modified Trace Function on SO(3)
Second, it can be shown that for each potential function in the family, there exists a subset of the family such that the synergistic gap is positive at the unwanted critical points.
3D-aware Image Generation using 2D Diffusion Models
In this paper, we introduce a novel 3D-aware image generation method that leverages 2D diffusion models.
3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision.
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding
We pretrained a large {\SST} model on a synthetic Structured3D dataset, which is an order of magnitude larger than the ScanNet dataset.
Ranked #2 on
3D Object Detection
on S3DIS
(using extra training data)
Locally Attentional SDF Diffusion for Controllable 3D Shape Generation
Our method is built on a two-stage diffusion model.
Global Stabilization of Antipodal Points on n-Sphere with Application to Attitude Tracking
Existing approaches to robust global asymptotic stabilization of a pair of antipodal points on unit $n$-sphere $\mathbb{S}^n$ typically involve the non-centrally synergistic hybrid controllers for attitude tracking on unit quaternion space.
Relighting Neural Radiance Fields with Shadow and Highlight Hints
This paper presents a novel neural implicit radiance representation for free viewpoint relighting from a small set of unstructured photographs of an object lit by a moving point light source different from the view position.
AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collections
For the new task, we base our method on the generative radiance manifold representation and equip it with learnable facial and head-shoulder deformations.
Adaptive conformal classification with noisy labels
This paper develops novel conformal prediction methods for classification tasks that can automatically adapt to random label contamination in the calibration sample, leading to more informative prediction sets with stronger coverage guarantees compared to state-of-the-art approaches.
"I'm Not Confident in Debiasing AI Systems Since I Know Too Little": Teaching AI Creators About Gender Bias Through Hands-on Tutorials
Gender bias is rampant in AI systems, causing bad user experience, injustices, and mental harm to women.
A Real-time Method for Inserting Virtual Objects into Neural Radiance Fields
We present the first real-time method for inserting a rigid virtual object into a neural radiance field, which produces realistic lighting and shadowing effects, as well as allows interactive manipulation of the object.
From Authority-Respect to Grassroots-Dissent: Degree-Weighted Social Learning and Convergence Speed
Opinions are influenced by neighbors, with varying degrees of emphasis based on their connections.
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Scene Segmentation
We introduce SAMPro3D for zero-shot 3D indoor scene segmentation.
StructRe: Rewriting for Structured Shape Modeling
Such a localized rewriting process enables probabilistic modeling of ambiguous structures and robust generalization across object categories.
Plan, Posture and Go: Towards Open-World Text-to-Motion Generation
Some works use the CLIP model to align the motion space and the text space, aiming to enable motion generation from natural language motion descriptions.
Advanced Unstructured Data Processing for ESG Reports: A Methodology for Structured Transformation and Enhanced Analysis
In the evolving field of corporate sustainability, analyzing unstructured Environmental, Social, and Governance (ESG) reports is a complex challenge due to their varied formats and intricate content.
A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars
The objective of this paper is to develop a functional system for translating spoken languages into sign languages, referred to as Spoken2Sign translation.
CPSDBench: A Large Language Model Evaluation Benchmark and Baseline for Chinese Public Security Domain
Large Language Models (LLMs) have demonstrated significant potential and effectiveness across multiple application domains.
DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation
To provide the content creator with fine-grained control over the lighting during image generation, we augment the text-prompt with detailed lighting information in the form of radiance hints, i. e., visualizations of the scene geometry with a homogeneous canonical material under the target lighting.
MVD$^2$: Efficient Multiview 3D Reconstruction for Multiview Diffusion
By finetuning pretrained large image diffusion models with 3D data, the MVD methods first generate multiple views of a 3D object based on an image or text prompt and then reconstruct 3D shapes with multiview 3D reconstruction.
Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors
We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation.
Quaternion-Based Attitude Stabilization Using Synergistic Hybrid Feedback With Minimal Potential Functions
This paper investigates the robust global attitude stabilization problem for a rigid-body system using quaternion-based feedback.
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
We introduce VASA, a framework for generating lifelike talking faces with appealing visual affective skills (VAS) given a single static image and a speech audio clip.
Learning Hierarchy-Aware Quaternion Knowledge Graph Embeddings with Representing Relations as 3D Rotations
It is crucial for knowledge graph embedding models to model and infer various relation patterns, such as symmetry/antisymmetry.
Improving Knowledge Graph Embedding Using Affine Transformations of Entities Corresponding to Each Relation
By using previous knowledge graph embedding methods, every entity in a knowledge graph is usually represented as a k-dimensional vector.
Knowledge Graph Embedding by Adaptive Limit Scoring Loss Using Dynamic Weighting Strategy
The recently proposed Limit-based Scoring Loss independently limits the range of positive and negative triplet scores.
