Kai Xu

61

Papers

175

Total Citations

Papers (61)

DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection

Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement

Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes

Learning Cross-hand Policies of High-DOF Reaching and Grasping

Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model

OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging

Progressive Correspondence Regenerator for Robust 3D Registration

Physical-aware Neural Radiance Fields for Efficient Exposure Correction

Wave-MambaAD: Wavelet-driven State Space Model for Multi-class Unsupervised Anomaly Detection

A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds

Diagnosing Pretrained Models for Out-of-distribution Detection

MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval

Enhancing Video Super-Resolution via Implicit Resampling-based Alignment

Practical Hamiltonian Monte Carlo on Riemannian Manifolds via Relativity Theory

Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding

GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding

Deep Demonstration Tracing: Learning Generalizable Imitator Policy for Runtime Imitation from a Single Demonstration

Im2Struct: Recovering 3D Shape Structure From a Single RGB Image

Spatiotemporal CNN for Video Object Segmentation

Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction

Shape2Motion: Joint Analysis of Motion Parts and Attributes From 3D Shapes

PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation

PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes

Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation

Learning in the Frequency Domain

AdaCoSeg: Adaptive Shape Co-Segmentation With Group Consistency Loss

MLCVNet: Multi-Level Context VoteNet for 3D Object Detection

Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation

Learning Fine-Grained Segmentation of 3D Shapes Without Part Labels

StablePose: Learning 6D Object Poses From Geometrically Stable Patches

RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures

Accelerating Video Object Segmentation With Compressed Video

DisARM: Displacement Aware Relation Module for 3D Detection

RayMVSNet: Learning Ray-Based 1D Implicit Fields for Accurate Multi-View Stereo

Decoupling Makes Weakly Supervised Local Feature Better

Geometric Transformer for Fast and Robust Point Cloud Registration

3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification

Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration

RestorGS: Depth-aware Gaussian Splatting for Efficient 3D Scene Restoration

Weakly-Supervised Single-View Image Relighting

BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration

Rescan: Inductive Instance Segmentation for Indoor RGBD Scans

2D3D-MATR: 2D-3D Matching Transformer for Detection-Free Registration Between Images and Point Clouds

Accurate and Fast Compressed Video Captioning

PlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View

SOCS: Semantically-Aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations

AutoTransition: Learning to Recommend Video Transition Effects

NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction From Multi-View Images

VideoDirector: Precise Video Editing via Text-to-Video Models

VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis

ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting

CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs

Self-supervised Learning of Hybrid Part-aware 3D Representations of 2D Gaussians and Superquadrics

Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction

MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos

Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference

Telescoping Density-Ratio Estimation

PIE-NET: Parametric Inference of Point Cloud Edges

A Bayesian-Symbolic Approach to Reasoning and Learning in Intuitive Physics

Targeted Neural Dynamical Modeling

Variational Russian Roulette for Deep Bayesian Nonparametrics