Abstract The task of Visual Place Recognition (VPR) aims to match a query image against
references from an extensive database of images from different places relying solely on …

Natural image matting algorithms aim to predict the transparency map (alpha-matte) with the
trimap guidance. However, the production of trimap often requires significant labor, which …

The hybrid of Convolutional Neural Network (CNN) and Vision Transformers (ViT)
architectures has emerged as a groundbreaking approach, pushing the boundaries of …

Existing natural image matting algorithms inevitably have flaws in their predictions on
difficult cases, and their one-step prediction manner cannot further correct these errors. In …

Abstract The hybrid of Convolutional Neural Network (CNN) and Vision Transformer (ViT)
architecture has emerged as a groundbreaking approach, pushing the boundaries of …

Depth estimation plays a crucial role in various tasks within endoscopic surgery, including
navigation, surface reconstruction, and augmented reality visualization. Despite the …

We present LayerDiffusion, an approach enabling large-scale pretrained latent diffusion
models to generate transparent images. The method allows generation of single transparent …

We propose SparseDC, a model for Depth Completion from Sparse and non-uniform inputs.
Unlike previous methods focusing on completing fixed distributions on benchmark datasets …

Text-to-image generation has achieved astonishing results yet precise spatial controllability
and prompt fidelity remain highly challenging. This limitation is typically addressed through …

Automatic and interactive matting largely improve image matting by respectively alleviating
the need for auxiliary input and enabling object selection. Due to different settings on …