SPoILeR uses multimodal pre-training to enable accurate novel view synthesis of infrared, polarimetric, and multispectral data from RGB-supervised fine-tuning on new scenes.
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
Introduces TASLE benchmark and MSLoc baseline for temporal localization and explanation of manipulated segments in long videos.
A Debye CZT-based wave-optics pipeline generates lens-diverse synthetic defocus blur datasets that improve cross-device deblurring generalization over existing real and synthetic data.
A GAN framework is trained on EAGLE simulation merger trees to generate new realistic trees for semi-analytic galaxy models at modest computational cost.
MAPE combines a channel-attention U-Net (SAPE) trained on multi-model adversarial examples scheduled by PPSA to eliminate perturbations, reporting over 95.1% average defense on CIFAR-10 and 71.5% on Mini-ImageNet against black-box transferable attacks.
Transfer learning with FaceNet and ViT backbones achieves verification accuracies up to 96.85% on dog faces and outperforms prior SOTA on cattle, with mixed results on primates.
citing papers explorer
-
Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesis
SPoILeR uses multimodal pre-training to enable accurate novel view synthesis of infrared, polarimetric, and multispectral data from RGB-supervised fine-tuning on new scenes.
-
Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
Introduces TASLE benchmark and MSLoc baseline for temporal localization and explanation of manipulated segments in long videos.
-
Realistic Compound-Lens Defocus Blur Synthesis
A Debye CZT-based wave-optics pipeline generates lens-diverse synthetic defocus blur datasets that improve cross-device deblurring generalization over existing real and synthetic data.
-
A Halo Merger Tree Generation and Evaluation Framework
A GAN framework is trained on EAGLE simulation merger trees to generate new realistic trees for semi-analytic galaxy models at modest computational cost.
-
MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination
MAPE combines a channel-attention U-Net (SAPE) trained on multi-model adversarial examples scheduled by PPSA to eliminate perturbations, reporting over 95.1% average defense on CIFAR-10 and 71.5% on Mini-ImageNet against black-box transferable attacks.
-
Beyond Humans: Multispecies Animal Face Recognition Using Transfer Learning
Transfer learning with FaceNet and ViT backbones achieves verification accuracies up to 96.85% on dog faces and outperforms prior SOTA on cattle, with mixed results on primates.