image reconstruction
Image reconstruction refers to the process of creating a new image from acquired data, often involving techniques that enhance image quality or recover lost data, using models to infer the most likely original image.
- A Closer Look at NTK Alignment: Linking Phase Transitions in Deep Image Regression
- ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning
- Dual-Comb Ghost Imaging with Transformer-Based Reconstruction for Optical Fiber Endomicroscopy
- Looking Into the Water by Unsupervised Learning of the Surface Shape
- Multimodal LiDAR-Camera Novel View Synthesis with Unified Pose-free Neural Fields
- Q-Insight: Understanding Image Quality via Visual Reinforcement Learning
- Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning
- Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport
- VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation
- Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation