光谱超分辨

入门学习

基础文章（用于明确任务设定）

稀疏表示方法

• Sparse Recovery of Hyperspectral Signal from Natural RGB Images
• In Defense of Shallow Learned Spectral Reconstruction from RGB Images

基础函数加权方法

• RGB to Spectral Reconstruction via Learned Basis Functions and Weights

基于流形的方法

• From RGB to Spectrum for Natural Scenes via Manifold-Based Mapping

基本代码实现（用于参考一般实现流程）

• MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction

• Pixel-Aware Deep Function-Mixture Network for Spectral Super-Resolution 没有数据集

横向文章（观其大略，拓宽视野）

• Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement
• In-Place Scene Labelling and Understanding with Implicit Scene Representation
• Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform
• Reconstruction of Hyperspectral Data From RGB Images With Prior Category Information
• Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding
• Distilling Semantic Priors from SAM to Efficient Image Restoration Models
• FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models

参考工作

扩散模型

• A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence 代码跑不动，寄
• diffusion-hyperfeatures.github.io
• The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation
• DiffIR: Efficient Diffusion Model for Image Restoration
• CONTROLLING VISION-LANGUAGE MODELS FOR UNIVERSAL IMAGE RESTORATION
• Ingredient-oriented Multi-Degradation Learning for Image Restoration
• CoSeR: Bridging Image and Language for Cognitive Super-Resolution
• HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models
• HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models
• Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology
• DiffIR: Efficient Diffusion Model for Image Restoration
• Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model
• Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
• Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion
• FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models
• Adding Conditional Control to Text-to-Image Diffusion Models
• Unsupervised Semantic Correspondence Using Stable Diffusion
• What the DAAM: Interpreting Stable Diffusion Using Cross Attention

非组合block（拓宽视野）

• Spectral imaging with deep learning
• 基于超表面的实时超光谱成像芯片
• 基于超构表面的光谱成像及应用研究进展
• Material Based Object Tracking in Hyperspectral Videos
• Stimuli-responsive active materials for dynamic control of light field
• Miniaturized spectrometers with a tunable van der Waals junction
• Deeply learned broadband encoding stochastic hyperspectral imaging
• Metasurface-empowered snapshot hyperspectral imaging with convex/deep (CODE) small-data learning theory
• Broadband miniaturized spectrometers with a van der Waals tunnel diode
• A platform for integrated spectrometers based on solution-processable semiconductors

语义分割

• Segment Anything
• Segment Anything in High Quality
• Efficient SAM (CVPR 2024 best paper)
• ZegCLIP (CVPR 2023) （没有什么眼前一亮的设计）

多模态

• Multimodality Helps Unimodality (CVPR 2022)
• CLIP (CVPR 2021)

MLLM 多模态大语言模型

Cross tasks

• Toward the Vectorization of the Hyperspectral Imagery

Auto Regressive

• Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction (CVPR 2024)

DERT

• Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement (CVPR 2024)

Cross-Task

• Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection (ICCV 2023)
• Task-aware Adaptive Learning for Cross-domain Few-shot Learning (ICCV 2023)

Multi-Task Learning，joint learning

• EMA-Net

current task

• Ingredient-oriented Multi-Degradation Learning for Image Restoration (看不懂，没有物理意义)

• Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE) (CLIP语义理解特攻)

• CLIP

• Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation (CVPR 2023) (多种统一表示)

• Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wild

• Spec-NeRF: Multi-Spectral Neural Radiance Fields

• Neural Super-Resolution for Real-time Rendering with Radiance Demodulation

语义分割

• TCL (CVPR 2023)

相机

• Learning and inference in the brain
• Distributed Hierarchical Processing in the Primate Cerebral Cortex
• The ventral visual pathway: An expanded neural framework for the processing of object quality
• Top-Down Visual Attention from Analysis by Synthesis (CVPR 2023)
• Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
• CLIP_as_RNN
• Quantitative Analysis of Connectivity in the Visual Cortex: Extracting Function from Structure