3260 papers • 126 benchmarks • 313 datasets
The objective of this challenge is to automate the process of estimating the soil parameters, specifically, potassium (KKK), phosphorus pentoxide (P2O5P_2O_5P2O5), 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.
(Image credit: Papersgraph)
These leaderboards are used to track progress in seeing-beyond-the-visible-8
Use these libraries to find seeing-beyond-the-visible-8 models and implementations
No subtasks available.
This work proposes a new method called large mask inpainting (LaMa), which generalizes surprisingly well to resolutions that are higher than those seen at train time, and achieves this at lower parameter&time costs than the competitive baselines.
This paper proposes the concept of online video inpainting for autonomous vehicles to expand the field of view, thereby enhancing scene visibility, perception, and system safety and introduces the FlowLens architecture, which explicitly employs optical flow and implicitly incorporates a novel clip-recurrent transformer for feature propagation.
This paper studies the fundamental problem of extrapolating visual context using deep generative models, i.e., extending image borders with plausible structure and details. This seemingly easy task actually faces many crucial technical challenges and has its unique properties. The two major issues are size expansion and one-side constraints. We propose a semantic regeneration network with several special contributions and use multiple spatial related losses to address these issues. Our results contain consistent structures and high-quality textures. Extensive experiments are conducted on various possible alternatives and related methods. We also explore the potential of our method for various interesting applications that can benefit research in a variety of fields.
This paper simultaneously fill missing regions in all input frames by self-attention, and proposes to optimize STTN by a spatial-temporal adversarial loss to show the superiority of the proposed model.
An End-to-End framework for Flow-Guided Video Inpainting (E2 FGVI) through elaborately designed three trainable modules, namely, flow completion, feature propagation, and content hallucination modules that can be Jointly optimized, leading to a more efficient and effective inpainting process.
This work proposes FuseFormer, a Transformer model designed for video inpainting via fine-grained feature fusion based on novel Soft Split and Soft Composition operations, which surpasses state-of-the-art methods in both quantitative and qualitative evaluations.
A patch-based auto-encoder P-VQVAE, where the encoder converts the masked image into non-overlapped patch tokens and the decoder recovers the masked regions from the inpainted tokens while keeping the unmasked regions unchanged is designed.
The AI4EO Hyperview challenge seeks machine learning methods that predict agriculturally relevant soil parameters (K, Mg, P2O5, pH) from airborne hyperspectral images. We present a hybrid model fusing Random Forest and K-nearest neighbor regressors that exploit the average spectral reflectance, as well as derived features such as gradients, wavelet coefficients, and Fourier transforms. The solution is computationally lightweight and improves upon the challenge baseline by 21.9%, with the first place on the public leaderboard. In addition, we discuss neural network architectures and potential future improvements.
Adding a benchmark result helps the community track progress.