Yulin Qian

This paper introduces a variational autoencoder network designed for video colorization using reference images, addressing the challenge of colorizing black-and-white videos. Although recent techniques perform well in some scenarios, they often struggle with color inconsistencies and artifacts in videos that feature complex scenes and long durations. To tackle this, we propose a variational autoencoder framework that incorporates spatio-temporal information for efficient video colorization. To improve temporal consistency, we unify semantic correspondence with color propagation, allowing for simultaneous guidance in colorizing grayscale video frames. Additionally, the variational autoencoder learns spatio-temporal feature representations by mapping video frames into a latent space through an encoder network. The decoder network then transforms these latent features back into color images. Compared to traditional coloring methods, our approach accurately captures temporal relationships between video frames, providing precise colorization while ensuring video consistency. To further enhance video quality, we apply a specialized loss function that constrains the generated output, ensuring that the colorized video remains spatio-temporally consistent and natural. Experimental results demonstrate that our method significantly improves the video colorization process.

Diffusion models are widely recognized in image generation for their ability to produce high-quality images from text prompts. As the demand for customized models grows, various methods have emerged to capture appearance features. However, the exploration of relations between entities, another crucial aspect of images, has been limited. This study focuses on enabling models to capture and generate high-level semantic images with specific relation concepts, which is a challenging task. To this end, we introduce the Inv-ReVersion framework, which uses inverse relations text expansion to separate the feature fusion of multiple entities in images. Additionally, we employ a weighted contrastive loss to emphasize part of speech, helping the model learn more abstract relation concepts. We also propose a high-frequency suppressor to reduce the time spent on learning low-frequency details, enhancing the model’s ability to generate image relations. Compared to existing baselines, our approach can more accurately generate relation concepts between entities without additional computational costs, especially in capturing abstract relation concepts.

With the continuous evolution of VR technology, VR devices have become more accessible to the general public. The immersive and realistic experience provided by VR makes the gaming domain a popular direction for its application. However, game development requires a strong ability to organize code effectively, whether for beginners or developers with years of experience in game companies. Design patterns, which are built upon object-oriented design principles, offer a software development approach that can effectively address these challenges. To this end, this paper takes our team's independently developed VR game - Knight's Adventure - as an example. It covers various aspects from game introduction and requirement analysis to overall framework design. Furthermore, it provides detailed explanations of several typical design patterns employed in the game, demonstrating their implementation methods. This article elucidates the application of multiple design patterns in VR game development and offers solutions to common issues and requirements faced by game developers during practical development.