SOTAVerified

Seeing Beyond the Visible

The objective of this challenge is to automate the process of estimating the soil parameters, specifically, potassium (KKK), phosphorus pentoxide (P2O5P_2O_5P2​O5​), magnesium (MgMgMg) and pHpHpH, through extracting them from the airborne hyperspectral images captured over agricultural areas in Poland (the exact locations are not revealed). To make the solution applicable in real-life use cases, all the parameters should be estimated as precisely as possible.

Papers

Showing 18 of 8 papers

TitleStatusHype
Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent TransformerCode1
Predicting Soil Properties from Hyperspectral Satellite ImagesCode1
Reduce Information Loss in Transformers for Pluralistic Image InpaintingCode1
Towards An End-to-End Framework for Flow-Guided Video InpaintingCode3
Resolution-robust Large Mask Inpainting with Fourier ConvolutionsCode3
FuseFormer: Fusing Fine-Grained Information in Transformers for Video InpaintingCode1
Learning Joint Spatial-Temporal Transformations for Video InpaintingCode1
Wide-Context Semantic Image ExtrapolationCode1
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FlowLensAverage PSNR20.5Unverified
2E2FGVIAverage PSNR19.45Unverified
3LaMaAverage PSNR18.98Unverified
4FuseFormerAverage PSNR18.91Unverified
5STTNAverage PSNR18.73Unverified
6PUTAverage PSNR18.7Unverified
7SRNAverage PSNR16.1Unverified