Deep networks have shown impressive performance in the image restoration tasks, such as image colorization. However, we find that previous approaches rely on the digital representation from single color model with a specific mapping function, a.k.a., color space, during the colorization pipeline. In this paper, we first investigate the modeling of different color spaces, and find each of them exhibiting distinctive characteristics with unique distribution of colors. The complementarity among multiple color spaces leads to benefits for the image colorization task. We present MultiColor, a new learning-based approach to automatically colorize grayscale images that combines clues from multiple color spaces. Specifically, we employ a set of dedicated colorization modules for individual color space. Within each module, a transformer decoder is first employed to refine color query embeddings and then a color mapper produces color channel prediction using the embeddings and semantic features. With these predicted color channels representing various color spaces, a complementary network is designed to exploit the complementarity and generate pleasing and reasonable colorized images. We conduct extensive experiments on real-world datasets, and the results demonstrate superior performance over the state-of-the-arts.

LiDAR-based Semantic Scene Completion (SSC) is crucial for enhancing environmental perception and ensuring safety in autonomous driving. However, current methods face challenges in balancing accuracy and computational efficiency. On the one hand, projection-based methods reduce complexity but often suffer from spatial information loss. On the other hand, voxel-based methods preserve 3D structures but are computationally expensive. To address these limitations, we introduce SplitOcc, a novel multi-resolution approach that utilizes low-resolution voxels to represent large structures (e.g., road) and high-resolution voxels for detailed objects (e.g., bicycle). By employing multi-resolution sparse semantic voxels, SplitOcc can understand and represent the environment efficiently and accurately. Furthermore, the proposed Multi-Label Loss and Delayed-Drop strategies improve accuracy by preserving key semantic details during reconstruction. Extensive experiments demonstrate that our SplitOcc outperforms existing state-of-the-art methods across multiple evaluation metrics, showing notable improvements in both perception accuracy and detail preservation.

Scene text spotting has achieved an impressive performance over recent years. Currently, most text localization methods are designed with the text line instance. We argue that building a character-level spotting network is more suited to recognize the Chinese of text and Chinese is also common in scene text images. In this paper, we explore an anchor-free spotting framework that treats a character as a single point. To better capture Chinese character features, we first use the Canny edge detectors and superimpose the obtained edge information onto the RGB image channel. After that, a feed-forward network is set up and the inference can be processed in a single network forward-pass, without complex post-processing steps. Experiments are performed on the Chinese text dataset and the quantitative comparisons demonstrate the effectiveness of the anchor-free approach.