Image Reconstruction
8개 벤치마크 · 논문 2,461편 · 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
Physics-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 ReconstructionSimplified Cross-Modal Calibration for Heterogeneous Event-RGB Stereo Systems
Accurate extrinsic calibration between event-based and frame-based cameras remains a practical bottleneck for heterogeneous stereo systems. Existing approaches often require sensor or target motion, precise synchronizati…
Image ReconstructionFlow Matching-Based PET Image Reconstruction
Generative models have shown strong potential for positron emission tomography (PET) image reconstruction. Although diffusion model-based reconstruction methods have demonstrated promising performance, they often require…
Image ReconstructionTISC: A Text-Driven Image Semantic Communication System for Faithful Reconstruction
Generative image semantic communication converts an image into a text description and then performs text-to-image reconstruction at the receiver via diffusion-based generative models. This paradigm has attracted broad at…
Semantic CommunicationImage Reconstruction