Related papers: Generative World Renderer
3D scene generation is in high demand across various domains, including virtual reality, gaming, and the film industry. Owing to the powerful generative capabilities of text-to-image diffusion models that provide reliable priors, the…
Pretrained video diffusion models provide powerful spatiotemporal generative priors, making them a natural foundation for robotic world models. While recent world-action models jointly optimize future videos and actions, they predominantly…
A recent trend among generalizable novel view synthesis methods is to learn a rendering operator acting over single camera rays. This approach is promising because it removes the need for explicit volumetric rendering, but it effectively…
In image-based camera localization systems, information about the environment is usually stored in some representation, which can be referred to as a map. Conventionally, most maps are built upon hand-crafted features. Recently, neural…
Thumbnails are widely used all over the world as a preview for digital images. In this work we propose a deep neural framework to generate thumbnails of any size and aspect ratio, even for unseen values during training, with high accuracy…
Video generation assessment is essential for ensuring that generative models produce visually realistic, high-quality videos while aligning with human expectations. Current video generation benchmarks fall into two main categories:…
Despite recent advances in Video Large Language Models (VideoLLMs), effectively understanding long-form videos remains a significant challenge. Perceiving lengthy videos containing thousands of frames poses substantial computational burden.…
Recently deep neutral networks have achieved promising performance for filling large missing regions in image inpainting tasks. They usually adopted the standard convolutional architecture over the corrupted image, leading to meaningless…
Creative generation is the synthesis of new, surprising, and valuable samples that reflect user intent yet cannot be envisioned in advance. This task aims to extend human imagination, enabling the discovery of visual concepts that exist in…
Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. However, they also introduce significant usability challenges,…
World models serve as essential building blocks toward Artificial General Intelligence (AGI), enabling intelligent agents to predict future states and plan actions by simulating complex physical interactions. However, existing interactive…
We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time…
The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control…
High Dynamic Range (HDR) content (i.e., images and videos) has a broad range of applications. However, capturing HDR content from real-world scenes is expensive and time-consuming. Therefore, the challenging task of reconstructing visually…
Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in vision-language models (VLMs) have enabled high-quality SVG generation by framing the problem as a code…
The real-time deployment of cascaded generative AI pipelines for applications like video translation is constrained by significant system-level challenges. These include the cumulative latency of sequential model inference and the quadratic…
Generation of photo-realistic images, semantic editing and representation learning are a few of many potential applications of high resolution generative models. Recent progress in GANs have established them as an excellent choice for such…
Evaluation of AI systems often requires synthetic test cases, particularly for rare or safety-critical conditions that are difficult to observe in operational data. Generative AI offers a promising approach for producing such data through…
Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resources, hampering their ability to generate high-fidelity…
Multimodal Large Language Models (MLLMs) have shown promising capabilities in generating Scalable Vector Graphics (SVG) via direct code synthesis. However, existing paradigms typically adopt an open-loop "blind drawing" approach, where…