Related papers: CT-1: Vision-Language-Camera Models Transfer Spati…
4D driving simulation is essential for developing realistic autonomous driving simulators. Despite advancements in existing methods for generating driving scenes, significant challenges remain in view transformation and spatial-temporal…
Perceptual studies demonstrate that conditional diffusion models excel at reconstructing video content aligned with human visual perception. Building on this insight, we propose a video compression framework that leverages conditional…
Generating realistic robotic manipulation videos is an important step toward unifying perception, planning, and action in embodied agents. While existing video diffusion models require large domain-specific datasets and struggle to…
Video captioning is a critical task in the field of multimodal machine learning, aiming to generate descriptive and coherent textual narratives for video content. While large vision-language models (LVLMs) have shown significant progress,…
Video generation has achieved remarkable progress with the introduction of diffusion models, which have significantly improved the quality of generated videos. However, recent research has primarily focused on scaling up model training,…
We present a target-aware video diffusion model that generates videos from an input image, in which an actor interacts with a specified target while performing a desired action. The target is defined by a segmentation mask, and the action…
Vision language tasks, such as answering questions about or generating captions that describe an image, are difficult tasks for computers to perform. A relatively recent body of research has adapted the pretrained transformer architecture…
Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial…
Text-conditioned diffusion models have emerged as powerful tools for high-quality video generation. However, enabling Interactive Video Generation (IVG), where users control motion elements such as object trajectory, remains challenging.…
Despite the significant advancements made by Diffusion Transformer (DiT)-based methods in video generation, there remains a notable gap with controllable camera pose perspectives. Existing works such as OpenSora do NOT adhere precisely to…
Generative modeling aims to transform random noise into structured outputs. In this work, we enhance video diffusion models by allowing motion control via structured latent noise sampling. This is achieved by just a change in data: we…
Visual Commonsense Reasoning (VCR) remains a significant yet challenging research problem in the realm of visual reasoning. A VCR model generally aims at answering a textual question regarding an image, followed by the rationale prediction…
3D convolution is powerful for video classification but often computationally expensive, recent studies mainly focus on decomposing it on spatial-temporal and/or channel dimensions. Unfortunately, most approaches fail to achieve a…
Specifying nuanced and compelling camera motion remains a significant hurdle for non-expert creators using generative tools, creating an "expressive gap" where generic text prompts fail to capture cinematic vision. This barrier limits…
Cinematic storytelling is profoundly shaped by the artful manipulation of photographic elements such as depth of field and exposure. These effects are crucial in conveying mood and creating aesthetic appeal. However, controlling these…
Image-to-video generation, which aims to generate a video starting from a given reference image, has drawn great attention. Existing methods try to extend pre-trained text-guided image diffusion models to image-guided video generation…
This work highlights that video world modeling, alongside vision-language pre-training, establishes a fresh and independent foundation for robot learning. Intuitively, video world models provide the ability to imagine the near future by…
In this work, we rethink the approach to video super-resolution by introducing a method based on the Diffusion Posterior Sampling framework, combined with an unconditional video diffusion transformer operating in latent space. The video…
Recent advancements in text-to-video (T2V) generation have leveraged diffusion models to enhance visual coherence in videos synthesized from textual descriptions. However, existing research primarily focuses on object motion, often…
Text-to-video generation has demonstrated promising progress with the advent of diffusion models, yet existing approaches are limited by dataset quality and computational resources. To address these limitations, this paper presents a…