Copertina

Teacher-Guided Causal Interventions for Image Denoising: Orthogonal Content-Noise Disentanglement in Vision Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jiang, Kuai, Ding, Zhaoyan, Zhang, Guijuan, Lu, Dianjie, Zheng, Zhuoran
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SSPFormer: Self-Supervised Pretrained Transformer for MRI Images
di: Li, Jingkai, et al.
Pubblicazione: (2026)

FlowLUT: Efficient Image Enhancement via Differentiable LUTs and Iterative Flow Matching
di: Hu, Liubing, et al.
Pubblicazione: (2025)

UHD-GPGNet: UHD Video Denoising via Gaussian-Process-Guided Local Spatio-Temporal Modeling
di: He, Weiyuan, et al.
Pubblicazione: (2026)

6thGrid-Net: Unified Remote Sensing Image Dehazing Based on Color Restoration and Edge-Preserving
di: Bai, Runci, et al.
Pubblicazione: (2026)

AgentPolyp: Accurate Polyp Segmentation via Image Enhancement Agent
di: Wang, Pu, et al.
Pubblicazione: (2025)

UniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt Guidance
di: Sun, Shuning, et al.
Pubblicazione: (2025)

Foggy Crowd Counting: Combining Physical Priors and KAN-Graph
di: Wang, Yuhao, et al.
Pubblicazione: (2025)

UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache
di: Wang, Pu, et al.
Pubblicazione: (2025)

Hazy Pedestrian Trajectory Prediction via Physical Priors and Graph-Mamba
di: Chen, Jian, et al.
Pubblicazione: (2025)

CAST-LUT: Tokenizer-Guided HSV Look-Up Tables for Purple Flare Removal
di: Wang, Pu, et al.
Pubblicazione: (2025)

UHD Image Deblurring via Autoregressive Flow with Ill-conditioned Constraints
di: Xin, Yucheng, et al.
Pubblicazione: (2026)

DeLiVR: Differential Spatiotemporal Lie Bias for Efficient Video Deraining
di: Sun, Shuning, et al.
Pubblicazione: (2025)

LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing
di: Wang, Yongcong, et al.
Pubblicazione: (2026)

4KDehazeFlow: Ultra-High-Definition Image Dehazing via Flow Matching
di: Chen, Xingchi, et al.
Pubblicazione: (2025)

Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration
di: Wu, Chen, et al.
Pubblicazione: (2024)

Unifying VLM-Guided Flow Matching and Spectral Anomaly Detection for Interpretable Veterinary Diagnosis
di: Wang, Pu, et al.
Pubblicazione: (2026)

RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement
di: Xin, Yucheng, et al.
Pubblicazione: (2026)

DCA-LUT: Deep Chromatic Alignment with 5D LUT for Purple Fringing Removal
di: Lu, Jialang, et al.
Pubblicazione: (2025)

UHD Low-Light Image Enhancement via Real-Time Enhancement Methods with Clifford Information Fusion
di: Wang, Xiaohan, et al.
Pubblicazione: (2026)

U-shaped Vision Mamba for Single Image Dehazing
di: Zheng, Zhuoran, et al.
Pubblicazione: (2024)

FreeEnhance: Tuning-Free Image Enhancement via Content-Consistent Noising-and-Denoising Process
di: Luo, Yang, et al.
Pubblicazione: (2024)

Empowering Vision Transformers with Multi-Scale Causal Intervention for Long-Tailed Image Classification
di: Yan, Xiaoshuo, et al.
Pubblicazione: (2025)

Spatial-Spectral Adaptive Fidelity and Noise Prior Reduction Guided Hyperspectral Image Denoising
di: Xie, Xuelin, et al.
Pubblicazione: (2026)

Real Noise Decoupling for Hyperspectral Image Denoising
di: Zhang, Yingkai, et al.
Pubblicazione: (2025)

FD-Vision Mamba for Endoscopic Exposure Correction
di: Zheng, Zhuoran, et al.
Pubblicazione: (2024)

Denoising Vision Transformers
di: Yang, Jiawei, et al.
Pubblicazione: (2024)

DenoiseSplat: Feed-Forward Gaussian Splatting for Noisy 3D Scene Reconstruction
di: Jiang, Fuzhen, et al.
Pubblicazione: (2026)

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising
di: Lu, Liying, et al.
Pubblicazione: (2025)

Denoising Vision Transformer Autoencoder with Spectral Self-Regularization
di: Xiang, Xunzhi, et al.
Pubblicazione: (2025)

Disentangling Instruction Influence in Diffusion Transformers for Parallel Multi-Instruction-Guided Image Editing
di: Liu, Hui, et al.
Pubblicazione: (2025)

Transforming Noise Distributions with Histogram Matching: Towards a Single Denoiser for All
di: Fu, Sheng, et al.
Pubblicazione: (2025)

Is Noise Conditioning Necessary for Denoising Generative Models?
di: Sun, Qiao, et al.
Pubblicazione: (2025)

Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach
di: Zhang, Taolin, et al.
Pubblicazione: (2024)

SGDFormer: One-stage Transformer-based Architecture for Cross-Spectral Stereo Image Guided Denoising
di: Zhang, Runmin, et al.
Pubblicazione: (2024)

Causal Disentanglement for Robust Long-tail Medical Image Generation
di: Nie, Weizhi, et al.
Pubblicazione: (2025)

Beyond Image Prior: Embedding Noise Prior into Conditional Denoising Transformer
di: Huang, Yuanfei, et al.
Pubblicazione: (2024)

Accurate Forgetting for All-in-One Image Restoration Model
di: Su, Xin, et al.
Pubblicazione: (2024)

FDS: Frequency-Aware Denoising Score for Text-Guided Latent Diffusion Image Editing
di: Ren, Yufan, et al.
Pubblicazione: (2025)

DualContrast: Unsupervised Disentangling of Content and Transformations with Implicit Parameterization
di: Uddin, Mostofa Rafid, et al.
Pubblicazione: (2024)

Xformer: Hybrid X-Shaped Transformer for Image Denoising
di: Zhang, Jiale, et al.
Pubblicazione: (2023)