Understanding dark scenes based on multi-modal image data is challenging, as both the
visible and auxiliary modalities provide limited semantic information for the task. Previous …

Adaptation of semantic segmentation networks to different visual conditions is vital for robust
perception in autonomous cars and robots. However, previous work has shown that most …

In unsupervised domain adaptation (UDA), where models are trained on source data (eg,
synthetic) and adapted to target data (eg, real-world) without target annotations, addressing …

Semantic segmentation is essential for comprehending images, but the process
necessitates a substantial amount of detailed annotations at the pixel level. Acquiring such …

Unsupervised cross-domain scene segmentation approach adapts the source model to the
target domain, which utilizes two-stage strategies to minimize the inter-domain and intra …

The increasing relevance of panoptic segmentation is tied to the advancements in
autonomous driving and AR/VR applications. However, the deployment of such models has …

Due to unaffordable computational costs, the regularized disparity in iterative stereo
matching is typically maintained at a lower resolution than the input. To regress the full …

Nighttime scenes are hard to semantically perceive with learned models and annotate for
humans. Thus, realistic synthetic nighttime data become all the more important for learning …

Semantic segmentation based on optical images can provide comprehensive scene
information for intelligent vehicle systems, thus aiding in scene perception and decision …

The rapid advancements in artificial intelligence (AI), particularly in generative AI and large
language models (LLMs), have profoundly impacted the creative industries by enabling …