Lin Gu

papers

988

total citations

papers (19)

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

CVPR 2024arXiv

242

citations

Multitask AET With Orthogonal Tangent Regularity for Dark Object Detection

ICCV 2021arXiv

153

citations

Goal-Oriented Gaze Estimation for Zero-Shot Learning

CVPR 2021arXiv

149

citations

Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

ICCV 2023arXiv

114

citations

Frequency-Adaptive Dilated Convolution for Semantic Segmentation

CVPR 2024arXiv

citations

Revisiting Domain Generalized Stereo Matching Networks From a Feature Consistency Perspective

CVPR 2022arXiv

citations

Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption

AAAI 2024arXiv

citations

Frequency Dynamic Convolution for Dense Image Prediction

CVPR 2025arXiv

citations

Exploring Resolution and Degradation Clues As Self-Supervised Signal for Low Quality Object Detection

ECCV 2022arXiv

citations

Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer

ICCV 2023arXiv

citations

EventPillars: Pillar-based Efficient Representations for Event Data

AAAI 2025

citations

Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification

ECCV 2022

citations

Semantic-guided Masked Mutual Learning for Multi-modal Brain Tumor Segmentation with Arbitrary Missing Modalities

AAAI 2025arXiv

citations

Feature Normalized Knowledge Distillation for Image Classification

ECCV 2020

citations

Lin Gu

papers (19)

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

Multitask AET With Orthogonal Tangent Regularity for Dark Object Detection

Goal-Oriented Gaze Estimation for Zero-Shot Learning

Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

Frequency-Adaptive Dilated Convolution for Semantic Segmentation

Revisiting Domain Generalized Stereo Matching Networks From a Feature Consistency Perspective

Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption

Frequency Dynamic Convolution for Dense Image Prediction

Exploring Resolution and Degradation Clues As Self-Supervised Signal for Low Quality Object Detection

When Semantic Segmentation Meets Frequency Aliasing

Robust Synthetic-to-Real Transfer for Stereo Matching

InsTaG: Learning Personalized 3D Talking Head from Few-Second Video

Frequency-Dynamic Attention Modulation For Dense Prediction

TdAttenMix: Top-Down Attention Guided Mixup

Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer

EventPillars: Pillar-based Efficient Representations for Event Data

Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification

Semantic-guided Masked Mutual Learning for Multi-modal Brain Tumor Segmentation with Arbitrary Missing Modalities

Feature Normalized Knowledge Distillation for Image Classification

papers (19)

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

Multitask AET With Orthogonal Tangent Regularity for Dark Object Detection

Goal-Oriented Gaze Estimation for Zero-Shot Learning

Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

Frequency-Adaptive Dilated Convolution for Semantic Segmentation

Revisiting Domain Generalized Stereo Matching Networks From a Feature Consistency Perspective

Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption

Frequency Dynamic Convolution for Dense Image Prediction

Exploring Resolution and Degradation Clues As Self-Supervised Signal for Low Quality Object Detection

When Semantic Segmentation Meets Frequency Aliasing

Robust Synthetic-to-Real Transfer for Stereo Matching

InsTaG: Learning Personalized 3D Talking Head from Few-Second Video

Frequency-Dynamic Attention Modulation For Dense Prediction

TdAttenMix: Top-Down Attention Guided Mixup

Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer

EventPillars: Pillar-based Efficient Representations for Event Data

Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification

Semantic-guided Masked Mutual Learning for Multi-modal Brain Tumor Segmentation with Arbitrary Missing Modalities

Feature Normalized Knowledge Distillation for Image Classification