SOTAVerified

Image Reconstruction

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 2143 papers

TitleStatusHype
The model is the message: Lightweight convolutional autoencoders applied to noisy imaging data for planetary science and astrobiology—0
3D Magnetic Inverse Routine for Single-Segment Magnetic Field Images—0
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationCode2
Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation—0
LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language ModelsCode1
Vision Transformer-Based Time-Series Image Reconstruction for Cloud-Filling Applications—0
Cloud-Aware SAR Fusion for Enhanced Optical Sensing in Space MissionsCode0
A Prior-Guided Joint Diffusion Model in Projection Domain for PET Tracer ConversionCode0
Client Selection Strategies for Federated Semantic Communications in Heterogeneous IoT Networks—0
Improved Image Reconstruction and Diffusion Parameter Estimation Using a Temporal Convolutional Network Model of Gradient Trajectory Errors—0
Imaging at the quantum limit with convolutional neural networksCode0
PF-LHM: 3D Animatable Avatar Reconstruction from Pose-free Articulated Human Images—0
Adaptive Multi-resolution Hash-Encoding Framework for INR-based Dental CBCT Reconstruction with Truncated FOV—0
SpectralAR: Spectral Autoregressive Visual Generation—0
Stroke-based Cyclic Amplifier: Image Super-Resolution at Arbitrary Ultra-Large Scales—0
Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomization—0
Low-Rank Augmented Implicit Neural Representation for Unsupervised High-Dimensional Quantitative MRI Reconstruction—0
sparseGeoHOPCA: A Geometric Solution to Sparse Higher-Order PCA Without Covariance Estimation—0
Image Reconstruction as a Tool for Feature Analysis—0
Adaptive Blind Super-Resolution Network for Spatial-Specific and Spatial-Agnostic Degradations—0
VIVAT: Virtuous Improving VAE Training through Artifact Mitigation—0
Generative Learning of Differentiable Object Models for Compositional Interpretation of Complex Scenes—0
NSD-Imagery: A benchmark dataset for extending fMRI vision decoding methods to mental imagery—0
ResPF: Residual Poisson Flow for Efficient and Physically Consistent Sparse-View CT Reconstruction—0
Personalized MR-Informed Diffusion Models for 3D PET Image Reconstruction—0
Enhancing Neural Autoregressive Distribution Estimators for Image Reconstruction—0
Tomographic Foundation Model -- FORCE: Flow-Oriented Reconstruction Conditioning Engine—0
RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report—0
unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary ReasoningCode0
Self-Supervised-ISAR-Net Enables Fast Sparse ISAR Imaging—0
Digital twins enable full-reference quality assessment of photoacoustic image reconstructions—0
Super-temporal-resolution Photoacoustic Imaging with Dynamic Reconstruction through Implicit Neural Representation in Sparse-view—0
LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter—0
Self-supervised feature learning for cardiac Cine MR image reconstructionCode0
Implicit Inversion turns CLIP into a DecoderCode0
Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object—0
Improving Brain-to-Image Reconstruction via Fine-Grained Text Bridging—0
MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning—0
DeepInverse: A Python package for solving imaging inverse problems with deep learningCode4
Deep Spectral Prior—0
MedITok: A Unified Tokenizer for Medical Image Synthesis and InterpretationCode1
Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport—0
SHaDe: Compact and Consistent Dynamic 3D Reconstruction via Tri-Plane Deformation and Latent Diffusion—0
Bidirectional Variational Autoencoders—0
Linear Convergence of Plug-and-Play Algorithms with Kernel DenoisersCode0
Dynadiff: Single-stage Decoding of Images from Continuously Evolving fMRICode1
VTBench: Evaluating Visual Tokenizers for Autoregressive Image GenerationCode1
CTLformer: A Hybrid Denoising Model Combining Convolutional Layers and Self-Attention for Enhanced CT Image Reconstruction—0
FreqSelect: Frequency-Aware fMRI-to-Image Reconstruction—0
BandRC: Band Shifted Raised Cosine Activated Implicit Neural Representations—0
Show:102550
← PrevPage 1 of 43Next →
All datasetsImageNetUltra-High Resolution Image Reconstruction BenchmarkEdge-to-HandbagsEdge-to-ShoesAudio SetImageNet 256x256Edge-to-ClothesSpike-X4K

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Taming-VQGAN (16x16)FID3.64—Unverified
2VQGAN-LC (16x16)FID2.62—Unverified
3MaskGIT-VQGAN (16x16)FID2.28—Unverified
4RQ-VAE (8x8x16)FID1.83—Unverified
5TiTok-S-128FID1.71—Unverified
6MaskBit (16x16)FID1.66—Unverified
7ViT-VQGAN (16x16)FID1.28—Unverified
8Open-Magvit2 (16x16)FID1.17—Unverified
9Mo-VQGAN (16x16x4)FID1.12—Unverified
10IBQ (16x16)FID1—Unverified
#ModelMetricClaimedVerifiedStatus
1VAR (16x16)rFID9.85—Unverified
2VQGAN (16x16)rFID5.95—Unverified
3LlamaGen (16x16)rFID5.59—Unverified
4Open-Magvit2 (16x16)rFID4.18—Unverified
5MGVQ (16x16x4)rFID1.59—Unverified
6SD-VAE (16x16)rFID1.07—Unverified
#ModelMetricClaimedVerifiedStatus
1pix2pixFID96.31—Unverified
2bFTFID74.9—Unverified
3Xian et al._FID60.85—Unverified
4PI-RECFID0.07—Unverified
#ModelMetricClaimedVerifiedStatus
1pix2pixFID197.49—Unverified
2bFTFID121.2—Unverified
3Xian et al._FID44.76—Unverified
4PI-RECFID0.02—Unverified
#ModelMetricClaimedVerifiedStatus
1Ours (STFT: magnitude, L1l=1) W-ReplicateSSIM0.88—Unverified
2Ours (STFT: magnitude, L1l=1) WS-ReplicateSSIM0.86—Unverified
#ModelMetricClaimedVerifiedStatus
1AugVAE-SLFID3.28—Unverified
2AugVAE-MLFID1.04—Unverified
#ModelMetricClaimedVerifiedStatus
1bFTFID58.4—Unverified
#ModelMetricClaimedVerifiedStatus
1SwinSFAverage PSNR39.61—Unverified