Related papers: Dreamland: Controllable World Creation with Simula…

Generating high-quality and diverse human images is an important yet challenging task in vision and graphics. However, existing generative models often fall short under the high diversity of clothing shapes and textures. Furthermore, the…

In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs. While plenty of works extend unconditional generative models and…

We introduce DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets. DreamCraft3D++ inherits the multi-stage generation process of DreamCraft3D, but replaces the time-consuming…

Despite large-scale pretraining endowing models with language and vision reasoning capabilities, improving their spatial reasoning capability remains challenging due to the lack of data grounded in the 3D world. While it is possible for…

Object manipulation in images aims to not only edit the object's presentation but also gift objects with motion. Previous methods encountered challenges in concurrently handling static editing and dynamic generation, while also struggling…

Generative models trained on internet data have revolutionized how text, image, and video content can be created. Perhaps the next milestone for generative models is to simulate realistic experience in response to actions taken by humans,…

The acquisition of large-scale and diverse demonstration data are essential for improving robotic imitation learning generalization. However, generating such data for complex manipulations is challenging in real-world settings. We introduce…

World models based on video generation demonstrate remarkable potential for simulating interactive environments but face persistent difficulties in two key areas: maintaining long-term content consistency when scenes are revisited and…

Existing generative approaches for guided image synthesis of multi-object scenes typically rely on 2D controls in the image or text space. As a result, these methods struggle to maintain and respect consistent three-dimensional geometric…

Large-scale diffusion models have achieved remarkable success in generating high-quality images from textual descriptions, gaining popularity across various applications. However, the generation of layered content, such as transparent…

3D world generation is essential for applications such as immersive content creation or autonomous driving simulation. Recent advances in 3D world generation have shown promising results; however, these methods are constrained by grid…

3D content creation from a single image is a long-standing yet highly desirable task. Recent advances introduce 2D diffusion priors, yielding reasonable results. However, existing methods are not hyper-realistic enough for post-generation…

Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number…

Several families of continual learning techniques have been proposed to alleviate catastrophic interference in deep neural network training on non-stationary data. However, a comprehensive comparison and analysis of limitations remains…

Capturing and labeling real-world 3D data is laborious and time-consuming, which makes it costly to train strong 3D models. To address this issue, recent works present a simple method by generating randomized 3D scenes without simulation…

Recent advances in conditional generative image models have enabled impressive results. On the one hand, text-based conditional models have achieved remarkable generation quality, by leveraging large-scale datasets of image-text pairs. To…

The generation of 3D models from real-world objects has often been accomplished through photogrammetry, i.e., by taking 2D photos from a variety of perspectives and then triangulating matched point-based features to create a textured mesh.…

Video generation models, as one form of world models, have emerged as one of the most exciting frontiers in AI, promising agents the ability to imagine the future by modeling the temporal evolution of complex scenes. In autonomous driving,…

Procedural Content Generation via Reinforcement Learning (PCGRL) foregoes the need for large human-authored data-sets and allows agents to train explicitly on functional constraints, using computable, user-defined measures of quality…

Text-to-level generation aims to translate natural language descriptions into structured game levels, enabling intuitive control over procedural content generation. While prior text-to-level generators are typically limited to a single game…