Related papers: Playable Environments: Video Manipulation in Space…
We present 3DScenePrompt, a framework that generates the next video chunk from arbitrary-length input while enabling precise camera control and preserving scene consistency. Unlike methods conditioned on a single image or a short clip, we…
We describe Generative Blocks World to interact with the scene of a generated image by manipulating simple geometric abstractions. Our method represents scenes as assemblies of convex 3D primitives, and the same scene can be represented by…
Predicting diverse object motions from a single static image remains challenging, as current video generation models often entangle object movement with camera motion and other scene changes. While recent methods can predict specific…
Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing video generation methods provide minimal physical control, and single-image-to-3D…
Spatial intelligence is foundational to AI systems that interact with the physical world, particularly in 3D scene generation and spatial comprehension. Current methodologies for 3D scene generation often rely heavily on predefined…
We propose a new framework for creating and easily manipulating 3D models of arbitrary objects using casually captured videos. Our core ingredient is a novel hierarchy deformation model, which captures motions of objects with a…
How can we tell whether a video has been sped up or slowed down? How can we generate videos at different speeds? Although videos have been central to modern computer vision research, little attention has been paid to perceiving and…
In geographic data videos, camera movements are frequently used and combined to present information from multiple perspectives. However, creating and editing camera movements requires significant time and professional skills. This work aims…
Action-conditioned video models offer a promising path to building general-purpose robot simulators that can improve directly from data. Yet, despite training on large-scale robot datasets, current state-of-the-art video models still…
Generating realistic animated videos from static images is an important area of research in computer vision. Methods based on physical simulation and motion prediction have achieved notable advances, but they are often limited to specific…
This paper investigates the player's body as a system capable of unfamiliar interactive movement achieved through digital mediation in a playful environment. Body interactions in both digital and non-digital environments can be considered…
Recent advances in text-to-3D scene generation have demonstrated significant potential to transform content creation across multiple industries. Although the research community has made impressive progress in addressing the challenges of…
The process of design and development of virtual environments can be supported by tools and frameworks, to save time in technical aspects and focusing on the content. In this paper we present an academic framework which provides several…
Generating flexible-view 3D scenes, including 360{\deg} rotation and zooming, from single images is challenging due to a lack of 3D data. To this end, we introduce FlexWorld, a novel framework consisting of two key components: (1) a strong…
Accurately simulating existing 3D objects and a wide variety of materials often demands expert knowledge and time-consuming physical parameter tuning to achieve the desired dynamic behavior. We introduce MotionPhysics, an end-to-end…
Generating free-viewpoint videos is critical for immersive VR/AR experience but recent neural advances still lack the editing ability to manipulate the visual perception for large dynamic scenes. To fill this gap, in this paper we propose…
We argue that 3-D first-person video games are a challenging environment for real-time multi-modal reasoning. We first describe our dataset of human game-play, collected across a large variety of 3-D first-person games, which is both…
World models allow autonomous agents to plan and explore by predicting the visual outcomes of different actions. However, for robot manipulation, it is challenging to accurately model the fine-grained robot-object interaction within the…
Agents capable of reasoning and planning in the real world require the ability of predicting the consequences of their actions. While world models possess this capability, they most often require action labels, that can be complex to obtain…
We tackle the challenges of synthesizing versatile, physically simulated human motions for full-body object manipulation. Unlike prior methods that are focused on detailed motion tracking, trajectory following, or teleoperation, our…