Xin Huang

papers

809

total citations

papers (22)

HDR-NeRF: High Dynamic Range Neural Radiance Fields

CVPR 2022arXiv

157

citations

NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing

CVPR 2020arXiv

145

citations

M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction

CVPR 2022arXiv

141

citations

HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation

CVPR 2024arXiv

101

citations

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers

CVPR 2023arXiv

citations

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

AAAI 2025arXiv

citations

Local Implicit Ray Function for Generalizable Radiance Field Representation

CVPR 2023arXiv

citations

Material Anything: Generating Materials for Any 3D Object via Diffusion

CVPR 2025arXiv

citations

MoE-LPR: Multilingual Extension of Large Language Models Through Mixture-of-Experts with Language Priors Routing

AAAI 2025arXiv

citations

Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion

CVPR 2025arXiv

citations

Improved Maximin Share Approximations for Chores by Bin Packing

AAAI 2025arXiv

citations

Reproducible Vision-Language Models Meet Concepts Out of Pre-Training

CVPR 2025

citations

Privileged Prior Information Distillation for Image Matting

AAAI 2024arXiv

citations

Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images

AAAI 2025

citations

Adaptive Prompt-Based Semantic Embedding with Inspire Potential of Implicit Knowledge for Cross-Modal Retrieval

AAAI 2025

citations

"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP"

ECCV 2022

citations

Photon-Efficient 3D Imaging with A Non-Local Neural Network

ECCV 2020

citations

G2L-CariGAN: Caricature Generation from Global Structure to Local Features

AAAI 2024

citations

PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation

AAAI 2025

citations

Xin Huang

papers (22)

HDR-NeRF: High Dynamic Range Neural Radiance Fields

NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing

M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction

HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

Local Implicit Ray Function for Generalizable Radiance Field Representation

Material Anything: Generating Materials for Any 3D Object via Diffusion

MoE-LPR: Multilingual Extension of Large Language Models Through Mixture-of-Experts with Language Priors Routing

Inverting the Imaging Process by Learning an Implicit Camera Model

Causal Composition Diffusion Model for Closed-loop Traffic Generation

A Retrospect to Multi-prompt Learning across Vision and Language

Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion

Improved Maximin Share Approximations for Chores by Bin Packing

Reproducible Vision-Language Models Meet Concepts Out of Pre-Training

Privileged Prior Information Distillation for Image Matting

Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images

Adaptive Prompt-Based Semantic Embedding with Inspire Potential of Implicit Knowledge for Cross-Modal Retrieval

"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP"

Photon-Efficient 3D Imaging with A Non-Local Neural Network

G2L-CariGAN: Caricature Generation from Global Structure to Local Features

PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation

papers (22)

HDR-NeRF: High Dynamic Range Neural Radiance Fields

NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing

M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction

HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

Local Implicit Ray Function for Generalizable Radiance Field Representation

Material Anything: Generating Materials for Any 3D Object via Diffusion

MoE-LPR: Multilingual Extension of Large Language Models Through Mixture-of-Experts with Language Priors Routing

Inverting the Imaging Process by Learning an Implicit Camera Model

Causal Composition Diffusion Model for Closed-loop Traffic Generation

A Retrospect to Multi-prompt Learning across Vision and Language

Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion

Improved Maximin Share Approximations for Chores by Bin Packing

Reproducible Vision-Language Models Meet Concepts Out of Pre-Training

Privileged Prior Information Distillation for Image Matting

Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images

Adaptive Prompt-Based Semantic Embedding with Inspire Potential of Implicit Knowledge for Cross-Modal Retrieval

"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP"

Photon-Efficient 3D Imaging with A Non-Local Neural Network

G2L-CariGAN: Caricature Generation from Global Structure to Local Features

PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation