Qixing Huang

51

Papers

417

Total Citations

Papers (51)

H3DNet: 3D Object Detection Using Hybrid Geometric Primitives

OmniGlue: Generalizable Feature Matching with Foundation Model Guidance

Normalized Spectral Map Synchronization

Translation Synchronization via Truncated Least Squares

CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images

Jigsaw++: Imagining Complete Shape Priors for Object Reassembly

TutteNet: Injective 3D Deformations by Composition of 2D Mesh Deformations

FiffDepth: Feed-forward Transformation of Diffusion-Based Generators for Detailed Depth Estimation

PASTA: Part-Aware Sketch-to-3D Shape Generation with Text-Aligned Prior

GenVDM: Generating Vector Displacement Maps From a Single Image

Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces

SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks

Distributable Consistent Multi-Object Matching

Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion

PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation

A Late Fusion CNN for Digital Matting

Fast and Robust Multi-Person 3D Pose Estimation From Multiple Views

Learning Transformation Synchronization

Path-Invariant Map Networks

Extreme Relative Pose Network Under Hybrid Representations

HybridPose: 6D Object Pose Estimation Under Hybrid Representations

Learning View Selection for 3D Scenes

StruMonoNet: Structure-Aware Monocular 3D Prediction

E-CIR: Event-Enhanced Continuous Intensity Recovery

FvOR: Robust Joint Shape and Pose Optimization for Few-View Object Reconstruction

InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition

MVS2D: Efficient Multi-View Stereo via Attention-Driven 2D Convolutions

Pose Synchronization Under Multiple Pair-Wise Relative Poses

Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach

K-Best Transformation Synchronization

Reconstructing Humans with a Biomechanically Accurate Skeleton

HPNet: Deep Primitive Segmentation Using Hybrid Representations

Scene Synthesis via Uncertainty-Driven Attribute Synchronization

Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning

A Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks

PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation

ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

Real3D: Towards Scaling Large Reconstruction Models with Real Images

HUMOTO: A 4D Dataset of Mocap Human Object Interactions

RayZer: A Self-supervised Large View Synthesis Model

DeblurSR: Event-Based Motion Deblurring under the Spiking Representation

GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors

Detector-Free Structure from Motion

Enhancing Implicit Shape Generators Using Topological Regularizations

Learning Dense Correspondence via 3D-Guided Cycle Consistency

Dense Human Body Correspondences Using Convolutional Networks

A Condition Number for Joint Optimization of Cycle-Consistent Networks

Dense Correspondences between Human Bodies via Learning Transformation Synchronization on Graphs

Jigsaw: Learning to Assemble Multiple Fractured Objects

SMAC: Simultaneous Mapping and Clustering Using Spectral Decompositions