Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
For vision-language models (VLMs), understanding the dynamic properties of objects and their interactions within 3D scenes from video is crucial for effective reasoning. In this work, we introduce a video question answering dataset SuperCLEVR-Physics that focuses on the dynamics properties of objects. We concentrate on physical concepts -- velocity, acceleration, and collisions within 4D scenes, where the model needs to fully understand these dynamics properties and answer the questions built on top of them. From the evaluation of a variety of current VLMs, we find that these models struggle with understanding these dynamic properties due to the lack of explicit knowledge about the spatial structure in 3D and world dynamics in time variants. To demonstrate the importance of an explicit 4D dynamics representation of the scenes in understanding world dynamics, we further propose NS-4Dynamics, a Neural-Symbolic model for reasoning on 4D Dynamics properties under explicit scene representation from videos. Using scene rendering likelihood combining physical prior distribution, the 4D scene parser can estimate the dynamics properties of objects over time to and interpret the observation into 4D scene representation as world states. By further incorporating neural-symbolic reasoning, our approach enables advanced applications in future prediction, factual reasoning, and counterfactual reasoning. Our experiments show that our NS-4Dynamics suppresses previous VLMs in understanding the dynamics properties and answering questions about factual queries, future prediction, and counterfactual reasoning. Moreover, based on the explicit 4D scene representation, our model is effective in reconstructing the 4D scenes and re-simulate the future or counterfactual events.
Code (1)
Tasks
counterfactualCounterfactual ReasoningFuture predictionQuestion AnsweringVideo Question AnsweringSimilar Papers 제목 키워드 기반
Learning Multi-Object Dynamics with Compositional Neural Radiance Fields
We present a method to learn compositional multi-object dynamics models from image observations based on implicit object encoders, Neural Radiance Fields (NeRFs), and graph neural networks. NeRFs have become a popular ch…
DecoderGraph Neural NetworkNeRFObjectCP4D: Compositional Physics-aware 4D Scene Generation
4D generation (\textit{i.e.}, dynamic 3D generation) has recently emerged as a rapidly growing research frontier due to its powerful spatiotemporal modeling capabilities. However, despite notable advances, existing appro…
Scene GenerationMotion Synthesis3D GenerationPhiP-G: Physics-Guided Text-to-3D Compositional Scene Generation
Text-to-3D asset generation has achieved significant optimization under the supervision of 2D diffusion priors. However, when dealing with compositional scenes, existing methods encounter several challenges: 1). failure …
Scene GenerationText to 3DFreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity
In this paper, we aim to model 3D scene geometry, appearance, and the underlying physics purely from multi-view videos. By applying various governing PDEs as PINN losses or incorporating physics simulation into neural ne…
Motion SegmentationDreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors
Dynamic 3D interaction has been attracting a lot of attention recently. However, creating such 4D content remains challenging. One solution is to animate 3D scenes with physics-based simulation, which requires manually a…