Hao Lu

papers

1,290

total citations

papers (25)

Learning to Upsample by Learning to Sample

ICCV 2023arXiv

452

citations

Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting

CVPR 2022arXiv

125

citations

ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer

ICCV 2023arXiv

citations

Robust Object Detection with Inaccurate Bounding Boxes

ECCV 2022arXiv

citations

Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting

AAAI 2024arXiv

citations

MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects

ECCV 2022arXiv

citations

Fast Full-frame Video Stabilization with Iterative Optimization

ICCV 2023arXiv

citations

Unifying Automatic and Interactive Matting with Pretrained ViTs

CVPR 2024

citations

Backdoor Contrastive Learning via Bi-level Trigger Optimization

ICLR 2024arXiv

citations

MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models

CVPR 2025arXiv

citations

In-Context Matting

CVPR 2024arXiv

citations

Towards Generalizable Multi-Camera 3D Object Detection via Perspective Rendering

AAAI 2025

citations

Training Matting Models Without Alpha Labels

AAAI 2025arXiv

citations

Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model

CVPR 2025arXiv

citations

TransView: Inside, Outside, and Across the Cropping View Boundaries

ICCV 2021

citations

Dual-GAN: Joint BVP and Noise Modeling for Remote Physiological Measurement

CVPR 2021

citations

Composing Photos Like a Photographer

CVPR 2021

citations

Hao Lu

papers (25)

Learning to Upsample by Learning to Sample

Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning

Point-Query Quadtree for Crowd Counting, Localization, and More

SAPA: Similarity-Aware Point Affiliation for Feature Upsampling

Learning Affinity-Aware Upsampling for Deep Image Matting

BokehMe: When Neural Rendering Meets Classical Rendering

Neuron Structure Modeling for Generalizable Remote Physiological Measurement

FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling

3D Instances as 1D Kernels

ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer

Robust Object Detection with Inaccurate Bounding Boxes

Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting

MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects

Fast Full-frame Video Stabilization with Iterative Optimization

Unifying Automatic and Interactive Matting with Pretrained ViTs

Backdoor Contrastive Learning via Bi-level Trigger Optimization

MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models

In-Context Matting

Towards Generalizable Multi-Camera 3D Object Detection via Perspective Rendering

Training Matting Models Without Alpha Labels

Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model

TransView: Inside, Outside, and Across the Cropping View Boundaries

Dual-GAN: Joint BVP and Noise Modeling for Remote Physiological Measurement

Composing Photos Like a Photographer

papers (25)

Learning to Upsample by Learning to Sample

Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning

Point-Query Quadtree for Crowd Counting, Localization, and More

SAPA: Similarity-Aware Point Affiliation for Feature Upsampling

Learning Affinity-Aware Upsampling for Deep Image Matting

BokehMe: When Neural Rendering Meets Classical Rendering

Neuron Structure Modeling for Generalizable Remote Physiological Measurement

FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling

3D Instances as 1D Kernels

ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer

Robust Object Detection with Inaccurate Bounding Boxes

Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting

MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects

Fast Full-frame Video Stabilization with Iterative Optimization

Unifying Automatic and Interactive Matting with Pretrained ViTs

Backdoor Contrastive Learning via Bi-level Trigger Optimization

MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models

In-Context Matting

Towards Generalizable Multi-Camera 3D Object Detection via Perspective Rendering

Training Matting Models Without Alpha Labels

Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model

TransView: Inside, Outside, and Across the Cropping View Boundaries

Dual-GAN: Joint BVP and Noise Modeling for Remote Physiological Measurement

Composing Photos Like a Photographer