A method is presented to estimate the fundamental matrix from time-direction-ambiguous correspondences extracted along smear paths in a single motion-blurred image, with uncertainty-aware sampling for robustness.
In: AAAI (2021)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
StableMTL repurposes latent diffusion models for multi-task learning from partially annotated synthetic data via unified latent loss, task encoding, and a multi-stream task-attention architecture, reporting outperformance on 7 tasks across 8 benchmarks.
citing papers explorer
-
Robust Fundamental Matrix Estimation from Single Image Motion Blur
A method is presented to estimate the fundamental matrix from time-direction-ambiguous correspondences extracted along smear paths in a single motion-blurred image, with uncertainty-aware sampling for robustness.
-
StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets
StableMTL repurposes latent diffusion models for multi-task learning from partially annotated synthetic data via unified latent loss, task encoding, and a multi-stream task-attention architecture, reporting outperformance on 7 tasks across 8 benchmarks.