5 accepted papers
Tracking any point (TAP) is a fundamental yet challenging task in computer vision, requiring high precision and long-term motion reasoning. Recent attempts to combine RGB frames and event streams have shown promise, yet they typically rely on synchronous or non-adaptive fusion, leading to temporal m
Recent advances in 3D Gaussian Splatting (3DGS) have enabled RGB-only SLAM systems to achieve high-fidelity scene representation. However, the heavy reliance of existing systems on photometric rendering loss for camera tracking undermines their robustness, especially in unbounded outdoor environment
Artistic style transfer aims to replicate an artist’s painting style in a different image. While existing pre-trained model-based methods can generate high-quality stylized images, they often lack precise control over stylistic elements. Recent approaches incorporating textual inversion offer more a…
It is well known that the number of aligned images in the single image super-resolution (SISR) models training is limited. Synthesizing data is an effective way to address this issue. However, many degradation models only consider using spatially-invariant blur kernels to blur high-resolution (HR) i…
Tracking any point based on image frames is constrained by frame rates, leading to instability in high-speed scenarios and limited generalization in real-world applications. To overcome these limitations, we propose an image-event fusion point tracker, FE-TAP, which combines the contextual informati