Related papers: PhysRVG: Physics-Aware Unified Reinforcement Learn…
Recent advancements in video generation have witnessed significant progress, especially with the rapid advancement of diffusion models. Despite this, their deficiencies in physical cognition have gradually received widespread attention -…
World models have become indispensable tools for embodied intelligence, serving as powerful simulators capable of generating realistic robotic videos while addressing critical data scarcity challenges. However, current embodied world models…
Can we learn the physics of matter in motion directly from images and video--and trust it? Answering this question requires integrating experiments, physics-based simulation, and data across traditionally separate disciplines. Much of this…
Recent progress in video generation has led to impressive visual quality, yet current models still struggle to produce results that align with real-world physical principles. To this end, we propose an iterative self-refinement framework…
Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, evaluating whether generated videos actually follow these…
Reconstructing simulation-ready deformable objects is important for vision, graphics, and robotics. Existing physics-driven methods can recover physical digital twins from videos, but they suffer from two fundamental limitations: they…
Modern foundational Multimodal Large Language Models (MLLMs) and video world models have advanced significantly in mathematical, common-sense, and visual reasoning, but their grasp of the underlying physics remains underexplored. Existing…
Synthetic data is crucial for advancing autonomous driving (AD) systems, yet current state-of-the-art video generation models, despite their visual realism, suffer from subtle geometric distortions that limit their utility for downstream…
Recent diffusion-based video generation models can synthesize visually plausible videos, yet they often struggle to satisfy physical constraints. A key reason is that most existing approaches remain single-stage: they entangle high-level…
Video generation models have shown strong potential as world models for autonomous driving simulation. However, existing approaches are primarily trained on real-world driving datasets, which mostly contain natural and safe driving…
Autonomous driving requires robust perception models trained on high-quality, large-scale multi-view driving videos for tasks like 3D object detection, segmentation and trajectory prediction. While world models provide a cost-effective…
We introduce PhysMotion, a novel framework that leverages principled physics-based simulations to guide intermediate 3D representations generated from a single image and input conditions (e.g., applied force and torque), producing…
Recent advances in video generation have shown remarkable potential for constructing world simulators. However, current models still struggle to produce physically consistent results, particularly when handling large-scale or complex…
Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rely on Supervised Fine-Tuning using synthetic datasets. At present, there is an extreme…
Video generation models are increasingly used as world simulators for storytelling, simulation, and embodied AI. As these models advance, a key question arises: do generated videos obey the physical laws of the real world? Existing…
Diffusion models can generate realistic videos, but existing methods rely on implicitly learning physical reasoning from large-scale text-video datasets, which is costly, difficult to scale, and still prone to producing implausible motions…
Recent video foundation models demonstrate impressive visual synthesis but frequently suffer from geometric inconsistencies. While existing methods attempt to inject 3D priors via architectural modifications, they often incur high…
Recent advances in diffusion-based and autoregressive video generation models have achieved remarkable visual realism. However, these models typically lack accurate physical alignment, failing to replicate real-world dynamics in object…
Creating a physical digital twin of a real-world object has immense potential in robotics, content creation, and XR. In this paper, we present PhysTwin, a novel framework that uses sparse videos of dynamic objects under interaction to…
Recent advancements in video generation have substantially improved visual quality and temporal coherence, making these models increasingly appealing for applications such as autonomous driving, particularly in the context of driving…