Hongdong Li

77

Papers

669

Total Citations

Papers (77)

Deep Subspace Clustering Networks

NeurIPS 2017arXiv

ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion

Adapting Fine-Grained Cross-View Localization to Areas without Fine Ground Truth

StraightPCF: Straight Point Cloud Filtering

Probability Density Geodesics in Image Diffusion Latent Space

Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic

FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images

Robust Optical Flow Estimation of Double-Layer Images Under Transparency or Reflection

Robust Multi-Body Feature Tracker: A Segmentation-Free Approach

Rolling Shutter Camera Relative Pose: Generalized Epipolar Geometry

Neural Aggregation Network for Video Face Recognition

Scalable Dense Non-Rigid Structure-From-Motion: A Grassmannian Perspective

Structure From Recurrent Motion: From Rigidity to Recurrency

Learning Joint Gait Representation via Quintuplet Loss Minimization

ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving

Lending Orientation to Neural Networks for Cross-View Geo-Localization

Deep Stacked Hierarchical Multi-Patch Network for Image Deblurring

Noise-Aware Unsupervised Deep Lidar-Stereo Fusion

The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation

Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes

Where Am I Looking At? Joint Location and Orientation Estimation by Cross-View Matching

Deblurring by Realistic Blurring

Joint 3D Instance Segmentation and Object Detection for Autonomous Driving

Channel Attention Based Iterative Residual Learning for Depth Map Super-Resolution

Transferring Cross-Domain Knowledge for Video Sign Language Recognition

Learning Optical Flow From a Few Matches

Deep Two-View Structure-From-Motion Revisited

Rethinking Class Relations: Absolute-Relative Supervised and Unsupervised Few-Shot Learning

ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring

Lighting, Reflectance and Geometry Estimation From 360deg Panoramic Stereo

Multi-View 3D Reconstruction of a Texture-Less Smooth Surface of Unknown Generic Reflectance

Self-Supervised Visibility Learning for Novel View Synthesis

Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration

PluckerNet: Learn To Register 3D Line Reconstructions

Align and Prompt: Video-and-Language Pre-Training With Entity Prompts

Neural Reflectance for Shape Recovery With Shadow Handling

Improving GAN Equilibrium by Raising Spatial Awareness

HDR-NeRF: High Dynamic Range Neural Radiance Fields

Beyond Cross-View Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image

MEGANE: Morphable Eyeglass and Avatar Network

Wide-Angle Rectification via Content-Aware Conformal Mapping

WildLight: In-the-Wild Inverse Rendering With a Flashlight

A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization

Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container

Inverting the Imaging Process by Learning an Implicit Camera Model

Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering With Corrupted and Incomplete Data

Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence

"Maximizing Rigidity" Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction From Multiple Perspective Views

Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map

Monocular Dense 3D Reconstruction of a Complex Dynamic Scene From Two Perspective Frames

Stochastic Attraction-Repulsion Embedding for Large Scale Image Localization

Learning Trajectory Dependencies for Human Motion Prediction

Learning To Estimate Hidden Motions With Global Motion Aggregation

Benchmarking Ultra-High-Definition Image Super-Resolution

View Consistent Purification for Accurate Cross-View Localization

Homography Guided Temporal Fusion for Road Line and Marking Segmentation

MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing

Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer

Few-shot Action Recognition with Permutation-invariant Attention

Deep Novel View Synthesis from Colored 3D Point Clouds

Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding

Self-Calibrating Photometric Stereo by Neural Inverse Rendering

Blind Image Decomposition

Ranking Models in Unlabeled New Environments

GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction

Improving Cancer Gene Prediction by Enhancing Common Information Between the PPI Network and Gene Functional Association

View From Above: Orthogonal-View aware Cross-view Localization

Dense, Accurate Optical Flow Estimation With Piecewise Parametric Model

Iteratively Reweighted Graph Cut for Multi-Label MRFs With Non-Convex Priors

Beyond Local Search: Tracking Objects Everywhere With Instance-Specific Proposals

Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization

TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation

Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation

Hierarchical Neural Architecture Search for Deep Stereo Matching

Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?

DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation

Neural Collaborative Subspace Clustering