The rise of 3D generative models has enabled automatic 3D geometry and texture synthesis from multimodal inputs (e.g., text or images). However, these methods often ignore physical constraints and manufacturability considerations. In this work, we address the challenge of producing 3D designs that are both lightweight and self-supporting. We present DensiCrafter, a framework for generating lightweight, self-supporting 3D hollow structures by optimizing the density field. Starting from coarse voxel grids produced by Trellis, we interpret these as continuous density fields to optimize and introduce three differentiable, physically constrained, and simulation-free loss terms. Additionally, a mass regularization penalizes unnecessary material, while a restricted optimization domain preserves the outer surface. Our method seamlessly integrates with pretrained Trellis-based models (e.g., Trellis, DSO) without any architectural changes. In extensive evaluations, we achieve up to 43% reduction in material mass on the text-to-3D task. Compared to state-of-the-art baselines, our method could improve the stability and maintain high geometric fidelity. Real-world 3D-printing experiments confirm that our hollow designs can be reliably fabricated and could be self-supporting.

Social media has fundamentally transformed how people access information and form social connections, with content expression playing a critical role in driving information diffusion. While prior research has focused largely on network structures and tipping point identification, it provides limited tools for automatically generating content tailored for virality within a specific audience. To fill this gap, we propose the novel task of Diffusion-Oriented Content Generation (DOCG) and introduce an information enhancement algorithm for generating content optimized for diffusion. Our method includes an influence indicator that enables content-level diffusion assessment without requiring access to network topology, and an information editor that employs reinforcement learning to explore interpretable editing strategies. The editor leverages generative models to produce semantically faithful, audience-aware textual or visual content. Experiments on real-world social media datasets and user study demonstrate that our approach significantly improves diffusion effectiveness while preserving the core semantics of the original content.

Freeform thin-shell surfaces are critical in various fields, but their fabrication is complex and costly. Traditional methods are wasteful and require custom molds, while 3D printing needs extensive support structures and post-processing. Thermal shrinkage actuated 4D printing is an effective method for fabricating 3D shell. However, existing research faces issues related to precise deformation and limited robustness. Addressing these issues is challenging due to three key factors: (1) Difficulty in finding a universal method to control deformation across different materials; (2) Variability in deformation influenced by factors such as printing speed, layer thickness, and heating temperature; (3) Environmental factors affecting the deformation process. To overcome these challenges, we introduce FreeShell, a robust 4D printing technique that uses thermal shrinkage to create precise 3D shells. This method prints triangular tiles connected by shrinkable connectors using a single material. Upon heating, the connectors shrink, moving the tiles to form the desired 3D shape, simplifying fabrication and reducing material and environment dependency. An optimized mesh layout algorithm computes suitable printing structures that satisfy the defined structural objectives. FreeShell demonstrates its effectiveness through various examples and experiments, showcasing precision, robustness, and strength, representing advancement in fabricating complex freeform surfaces.

Embedded data visualizations have emerged as a powerful narrative medium for conveying complex information within video footage. However, creating such content remains labor-intensive, as existing workflows rely on manual frame-by-frame adjustments to ensure spatial and temporal consistency. To address these challenges, we present ChartBlender, an interactive authoring system designed to streamline the creation, embedding, and automatic synchronization of data visualizations within video scenes. We develop a tracking pipeline that supports both object and camera tracking, ensuring robust alignment of visualizations with dynamic video content. To maintain visual clarity and aesthetic coherence, we also explore the design space of video-suited visualizations and develop a library of customizable templates optimized for video embedding. We evaluated ChartBlender through two controlled experiments and expert interviews with five domain experts. Results show that our system enables accurate synchronization and accelerates the production of data-driven videos.

Music videos, as a prevalent form of multimedia entertainment, deliver engaging audio-visual experiences to audiences and have gained immense popularity among singers and fans. Creators can express their interpretations of music naturally through visual elements. However, the creation process of music video demands proficiency in script design, video shooting, and music-video synchronization, posing significant challenges for non-professionals. Previous work has designed automated music video generation frameworks. However, they suffer from complexity in input and poor output quality. In response, we present MV-Crafter, a system capable of producing high-quality music videos with synchronized music-video rhythm and style. Our approach involves three technical modules that simulate the human creation process: the script generation module, video generation module, and music-video synchronization module. MV-Crafter leverages a large language model to generate scripts considering the musical semantics. To address the challenge of synchronizing short video clips with music of varying lengths, we propose a dynamic beat-matching algorithm and visual envelope-induced warping method to ensure precise, monotonic music-video synchronization. Besides, we design a user-friendly interface to simplify the creation process with intuitive editing features. Extensive experiments have demonstrated that MV-Crafter provides an effective solution for improving the quality of generated music videos.

Personalizing products aesthetically or functionally can help users increase personal relevance and support self-expression. However, using non-abstract personal data such as head portraits for product personalization has been understudied. While recent advances in Artificial Intelligence have enabled generating stylized head portraits, these images also raise concerns about lack of control, artificiality, and ethics, which potentially limit their broader use. In this work, we present PicMe, a design support tool that converts user face photos into stylized head portraits as vector graphics that can be used to personalize products. To enable style transfer, PicMe leverages a deep-learning-based algorithm trained on an extended open-source illustration dataset of characters in a cartoonish and minimalistic style. We evaluated PicMe through two experiments and a user study. The results of our evaluation showed that PicMe can help create personalized head portraits that support self-expression.

The development of face editing has been boosted since the birth of StyleGAN. While previous works have explored different interactive methods, such as sketching and exemplar photos, they have been limited in terms of expressiveness and generality. In this paper, we propose a new interaction method by guiding the editing with abstract clipart, composed of a set of simple semantic parts, allowing users to control across face photos with simple clicks. However, this is a challenging task given the large domain gap between colorful face photos and abstract clipart with limited data. To solve this problem, we introduce a frame-work called ClipFaceShop1built on top of StyleGAN. The key idea is to take advantage of $\mathcal{W} +$ latent code encoded rich and disentangled visual features, and create a new lightweight selective feature adaptor to predict a modifiable path toward the target output photo. Since no pairwise labeled data exists for training, we design a set of losses to provide supervision signals for learning the modifiable path. Experimental results show that ClipFaceShop generates realistic and faithful face photos, sharing the same facial attributes as the reference clipart. We demonstrate that ClipFaceShop supports clipart in diverse styles, even in form of a free-hand sketch.