Image Reconstruction
8개 벤치마크 · 논문 2,464편 · 이 태스크의 논문 보기 →
Benchmarks
ImageNet
Edge-to-Handbags
Edge-to-Shoes
Audio Set
ImageNet 256x256
Edge-to-Clothes
Spike-X4K
Most implemented
High-Resolution Image Synthesis with Latent Diffusion Models
Unsupervised Monocular Depth Estimation with Left-Right Consistency
Digging Into Self-Supervised Monocular Depth Estimation
Universal Style Transfer via Feature Transforms
Taming Transformers for High-Resolution Image Synthesis
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
Papers
DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff between reconstruction fidelity and generation efficiency: high compres…
Text-to-Image GenerationImage ReconstructionOn the Diffusibility of High-Dimensional Latents
Representation Autoencoders (RAEs) enable diffusion models to operate in the feature spaces of pretrained visual encoders. However, many off-the-shelf encoders are not optimized for faithful reconstruction, discarding fi…
Text-to-Image GenerationImage ReconstructionHybrid Variational Quantum Circuits for Multivariate Regression and High-Dimensional Data Reconstruction
Variational quantum circuits (VQCs) are parameterized quantum circuits optimized classically. We propose a hybrid variational quantum circuit (HVQC) extending VQCs with a classical affine post-measurement layer, enabling…
Image ReconstructionPhysics-Guided Flow Matching for CT Image Reconstruction
Deep generative models have recently emerged as powerful priors for solving ill-posed inverse problems in CT, with diffusion-based approaches achieving state-of-the-art reconstruction performance. However, diffusion mode…
Computational EfficiencyImage ReconstructionData AugmentationGAN-Based Semantic Communication for Image Transmission in IoV
For cooperative perception in the internet of vehicles, this paper proposes a generative adversarial network-based semantic communication framework to address the efficiency and fidelity bottlenecks of traditional commun…
Semantic CommunicationSemantic SegmentationImage ReconstructionTissue-Mixture Entropy-Weighted Reconstruction for Partial-Volume-Aware Brain MRI Super-Resolution
Full-image objectives in brain magnetic resonance imaging (MRI) super-resolution (SR) can underweight tissue-transition regions affected by the partial-volume effect (PVE), as these regions occupy only a small fraction o…
Image Reconstruction