Forecasting Future Videos from Novel Views via Disentangled 3D Scene Representation

• URL: http://arxiv.org/abs/2407.21450v2
• Date: Fri, 2 Aug 2024 05:01:38 GMT
• Title: Forecasting Future Videos from Novel Views via Disentangled 3D Scene Representation
• Authors: Sudhir Yarram, Junsong Yuan,
• Abstract summary: We learn an entangled representation, aiming to model layered scene geometry, motion forecasting and novel view synthesis together. Our approach chooses to disentangle scene geometry from scene motion, via lifting the 2D scene to 3D point clouds. To model future 3D scene motion, we propose a disentangled two-stage approach that initially forecasts ego-motion and subsequently the residual motion of dynamic objects.
• Score: 54.60804602905519
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video extrapolation in space and time (VEST) enables viewers to forecast a 3D scene into the future and view it from novel viewpoints. Recent methods propose to learn an entangled representation, aiming to model layered scene geometry, motion forecasting and novel view synthesis together, while assuming simplified affine motion and homography-based warping at each scene layer, leading to inaccurate video extrapolation. Instead of entangled scene representation and rendering, our approach chooses to disentangle scene geometry from scene motion, via lifting the 2D scene to 3D point clouds, which enables high quality rendering of future videos from novel views. To model future 3D scene motion, we propose a disentangled two-stage approach that initially forecasts ego-motion and subsequently the residual motion of dynamic objects (e.g., cars, people). This approach ensures more precise motion predictions by reducing inaccuracies from entanglement of ego-motion with dynamic object motion, where better ego-motion forecasting could significantly enhance the visual outcomes. Extensive experimental analysis on two urban scene datasets demonstrate superior performance of our proposed method in comparison to strong baselines.

Related papers

• Shape of Motion: 4D Reconstruction from a Single Video [51.04575075620677]
  We introduce a method capable of reconstructing generic dynamic scenes, featuring explicit, full-sequence-long 3D motion. We exploit the low-dimensional structure of 3D motion by representing scene motion with a compact set of SE3 motion bases. Our method achieves state-of-the-art performance for both long-range 3D/2D motion estimation and novel view synthesis on dynamic scenes.
  arXiv  Detail & Related papers  (2024-07-18T17:59:08Z)
• DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perception [54.02566476357383]
  We propose the first Dynamic Environment MOtion Synthesis framework (DEMOS) to predict future motion instantly according to the current scene. We then use it to dynamically update the latent motion for final motion synthesis. The results show our method outperforms previous works significantly and has great performance in handling dynamic environments.
  arXiv  Detail & Related papers  (2024-03-04T05:38:16Z)
• Decoupling Dynamic Monocular Videos for Dynamic View Synthesis [50.93409250217699]
  We tackle the challenge of dynamic view synthesis from dynamic monocular videos in an unsupervised fashion. Specifically, we decouple the motion of the dynamic objects into object motion and camera motion, respectively regularized by proposed unsupervised surface consistency and patch-based multi-view constraints.
  arXiv  Detail & Related papers  (2023-04-04T11:25:44Z)
• Diffusion-based Generation, Optimization, and Planning in 3D Scenes [89.63179422011254]
  We introduce SceneDiffuser, a conditional generative model for 3D scene understanding. SceneDiffuser is intrinsically scene-aware, physics-based, and goal-oriented. We show significant improvements compared with previous models.
  arXiv  Detail & Related papers  (2023-01-15T03:43:45Z)
• 3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators [24.181604511269096]
  We propose an action-conditioned dynamics model that predicts scene changes caused by object and agent interactions in a viewpoint-in 3D neural scene representation space. In this space, objects do not interfere with one another and their appearance persists over time and across viewpoints. We show our model generalizes well its predictions across varying number and appearances of interacting objects as well as across camera viewpoints.
  arXiv  Detail & Related papers  (2020-11-12T16:15:52Z)
• Future Video Synthesis with Object Motion Prediction [54.31508711871764]
  Instead of synthesizing images directly, our approach is designed to understand the complex scene dynamics. The appearance of the scene components in the future is predicted by non-rigid deformation of the background and affine transformation of moving objects. Experimental results on the Cityscapes and KITTI datasets show that our model outperforms the state-of-the-art in terms of visual quality and accuracy.
  arXiv  Detail & Related papers  (2020-04-01T16:09:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.