Related papers: NUWA-Infinity: Autoregressive over Autoregressive …
Novel view synthesis from a single input image is a challenging task, where the goal is to generate a new view of a scene from a desired camera pose that may be separated by a large motion. The highly uncertain nature of this synthesis task…
Autoregressive generative models naturally generate variable-length sequences, while non-autoregressive models struggle, often imposing rigid, token-wise structures. We propose Edit Flows, a non-autoregressive model that overcomes these…
We introduce bounded generation as a generalized task to control video generation to synthesize arbitrary camera and subject motion based only on a given start and end frame. Our objective is to fully leverage the inherent generalization…
We propose Infinite-World, a robust interactive world model capable of maintaining coherent visual memory over 1000+ frames in complex real-world environments. While existing world models can be efficiently optimized on synthetic data with…
While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models are inherently…
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…
Modern GPUs feature specialized hardware units that enable high-performance, asynchronous dataflow execution. However, the conventional SIMT programming model is fundamentally misaligned with this task-parallel hardware, creating a…
We present Wan-Image, a unified visual generation system explicitly engineered to paradigm-shift image generation models from casual synthesizers into professional-grade productivity tools. While contemporary diffusion models excel at…
Generative AI is transforming image synthesis, enabling the creation of high-quality, diverse, and photorealistic visuals across industries like design, media, healthcare, and autonomous systems. Advances in techniques such as…
We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…
World models aim to endow AI systems with the ability to represent, generate, and interact with dynamic environments in a coherent and temporally consistent manner. While recent video generation models have demonstrated impressive visual…
Diffusion models have recently achieved remarkable results for video generation. Despite the encouraging performances, the generated videos are typically constrained to a small number of frames, resulting in clips lasting merely a few…
Autoregressive modeling has been a huge success in the field of natural language processing (NLP). Recently, autoregressive models have emerged as a significant area of focus in computer vision, where they excel in producing high-quality…
We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard…
Currently almost all state-of-the-art novel view synthesis and reconstruction models rely on calibrated cameras or additional geometric priors for training. These prerequisites significantly limit their applicability to massive uncalibrated…
Despite increasingly realistic image quality, recent 3D image generative models often operate on 3D volumes of fixed extent with limited camera motions. We investigate the task of unconditionally synthesizing unbounded nature scenes,…
Rendering photo-realistic novel-view images of complex scenes has been a long-standing challenge in computer graphics. In recent years, great research progress has been made on enhancing rendering quality and accelerating rendering speed in…
Generating high-quality 360{\deg} panoramic videos from perspective input is one of the crucial applications for virtual reality (VR), whereby high-resolution videos are especially important for immersive experience. Existing methods are…
Large image diffusion models enable novel view synthesis with high quality and excellent zero-shot capability. However, such models based on image-to-image translation have no guarantee of view consistency, limiting the performance for…
Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using…