Feng Yang

papers

3,815

total citations

papers (21)

VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining

CVPR 2023arXiv

citations

COMISR: Compression-Informed Video Super-Resolution

ICCV 2021arXiv

citations

Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them From 2D Renderings

CVPR 2022arXiv

citations

Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection

ICCV 2023arXiv

citations

Calibrated Multi-Preference Optimization for Aligning Diffusion Models

CVPR 2025arXiv

citations

WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights

CVPR 2024arXiv

citations

3D-GSW: 3D Gaussian Splatting for Robust Watermarking

CVPR 2025arXiv

citations

Cropper: Vision-Language Model for Image Cropping through In-Context Learning

CVPR 2025arXiv

citations

GIFnets: Differentiable GIF Encoding Framework

CVPR 2020arXiv

citations

Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation

CVPR 2025arXiv

citations

ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling

ECCV 2024arXiv

citations

Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion Model

AAAI 2025arXiv

citations

Rich Features for Perceptual Quality Assessment of UGC Videos

CVPR 2021

citations

CounterPC: Counterfactual Feature Realignment for Unsupervised Domain Adaptation on Point Clouds

ICCV 2025

citations

Feng Yang

papers (21)

MUSIQ: Multi-Scale Image Quality Transformer

MaxViT: Multi-axis Vision Transformer

MAXIM: Multi-Axis MLP for Image Processing

SVDiff: Compact Parameter Space for Diffusion Fine-Tuning

Distortion Agnostic Deep Watermarking

Adversarially Adaptive Normalization for Single Domain Generalization

Rich Human Feedback for Text-to-Image Generation

VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining

COMISR: Compression-Informed Video Super-Resolution

Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them From 2D Renderings

Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection

Calibrated Multi-Preference Optimization for Aligning Diffusion Models

WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights

3D-GSW: 3D Gaussian Splatting for Robust Watermarking

Cropper: Vision-Language Model for Image Cropping through In-Context Learning

GIFnets: Differentiable GIF Encoding Framework

Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation

ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling

Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion Model

Rich Features for Perceptual Quality Assessment of UGC Videos

CounterPC: Counterfactual Feature Realignment for Unsupervised Domain Adaptation on Point Clouds

papers (21)

MUSIQ: Multi-Scale Image Quality Transformer

MaxViT: Multi-axis Vision Transformer

MAXIM: Multi-Axis MLP for Image Processing

SVDiff: Compact Parameter Space for Diffusion Fine-Tuning

Distortion Agnostic Deep Watermarking

Adversarially Adaptive Normalization for Single Domain Generalization

Rich Human Feedback for Text-to-Image Generation

VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining

COMISR: Compression-Informed Video Super-Resolution

Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them From 2D Renderings

Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection

Calibrated Multi-Preference Optimization for Aligning Diffusion Models

WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights

3D-GSW: 3D Gaussian Splatting for Robust Watermarking

Cropper: Vision-Language Model for Image Cropping through In-Context Learning

GIFnets: Differentiable GIF Encoding Framework

Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation

ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling

Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion Model

Rich Features for Perceptual Quality Assessment of UGC Videos

CounterPC: Counterfactual Feature Realignment for Unsupervised Domain Adaptation on Point Clouds