Related papers: MotionCrafter: One-Shot Motion Customization of Di…
We present a new method for text-driven motion transfer - synthesizing a video that complies with an input text prompt describing the target objects and scene while maintaining an input video's motion and scene layout. Prior methods are…
Generating videos guided by camera trajectories poses significant challenges in achieving consistency and generalizability, particularly when both camera and object motions are present. Existing approaches often attempt to learn these…
Text-to-image (T2I) customization empowers users to adapt the T2I diffusion model to new concepts absent in the pre-training dataset. On this basis, capturing multiple new concepts from a single image has emerged as a new task, allowing the…
This paper studies the human image animation task, which aims to generate a video of a certain reference identity following a particular motion sequence. Existing animation works typically employ the frame-warping technique to animate the…
Human facial images encode a rich spectrum of information, encompassing both stable identity-related traits and mutable attributes such as pose, expression, and emotion. While recent advances in image generation have enabled high-quality…
Text-guided generative diffusion models unlock powerful image creation and editing tools. While these have been extended to video generation, current approaches that edit the content of existing footage while retaining structure require…
With the increasing popularity of autonomous driving based on the powerful and unified bird's-eye-view (BEV) representation, a demand for high-quality and large-scale multi-view video data with accurate annotation is urgently required.…
Recent video-based world models have made pixel-space environments interactive at the camera level: users can navigate viewpoints while the model generates coherent visual continuations. Yet their action spaces remain incomplete: users can…
Controllability, temporal coherence, and detail synthesis remain the most critical challenges in video generation. In this paper, we focus on a commonly used yet underexplored cinematic technique known as Frame In and Frame Out.…
Recent video diffusion models have made remarkable strides in visual quality, yet precise, fine-grained control remains a key bottleneck that limits practical customizability for content creation. For AI video creators, three forms of…
We propose a novel architecture UniTransfer, which introduces both spatial and diffusion timestep decomposition in a progressive paradigm, achieving precise and controllable video concept transfer. Specifically, in terms of spatial…
Digital creators, from indie filmmakers to animation studios, face a persistent bottleneck: translating their creative vision into precise camera movements. Despite significant progress in computer vision and artificial intelligence,…
We introduce PartCrafter, the first structured 3D generative model that jointly synthesizes multiple semantically meaningful and geometrically distinct 3D meshes from a single RGB image. Unlike existing methods that either produce…
We present SpaceTimePilot, a video diffusion model that disentangles space and time for controllable generative rendering. Given a monocular video, SpaceTimePilot can independently alter the camera viewpoint and the motion sequence within…
This paper presents a method that allows users to design cinematic video shots in the context of image-to-video generation. Shot design, a critical aspect of filmmaking, involves meticulously planning both camera movements and object…
This paper presents a novel approach for exploring diverse and expressive motions that are physically correct and interactive. The approach combining user participation in with the animation development process using crowdsourcing to remove…
Real-time in-between motion generation is universally required in games and highly desirable in existing animation pipelines. Its core challenge lies in the need to satisfy three critical conditions simultaneously: quality, controllability…
Recent advances in text-to-video diffusion models have enabled high-fidelity and temporally coherent videos synthesis. However, current models are predominantly optimized for single-event generation. When handling multi-event prompts,…
Recent advancements in human video synthesis have enabled the generation of high-quality videos through the application of stable diffusion models. However, existing methods predominantly concentrate on animating solely the human element…
Object-level manipulation, relocating or reorienting objects in images or videos while preserving scene realism, is central to film post-production, AR, and creative editing. Yet existing methods struggle to jointly achieve three core…