On the Benefits of Instance Decomposition in Video Prediction Models
- URL: http://arxiv.org/abs/2501.10562v1
- Date: Fri, 17 Jan 2025 21:36:06 GMT
- Title: On the Benefits of Instance Decomposition in Video Prediction Models
- Authors: Eliyas Suleyman, Paul Henderson, Nicolas Pugeault,
- Abstract summary: State-of-the-art video prediction methods typically model the dynamics of a scene jointly and implicitly, without any explicit decomposition into separate objects.
This is challenging and potentially sub-optimal, as every object in a dynamic scene has their own pattern of movement, typically somewhat independent of others.
In this paper, we investigate the benefit of explicitly modeling the objects in a dynamic scene separately within the context of latent-transformer video prediction models.
- Score: 5.653106385738823
- License:
- Abstract: Video prediction is a crucial task for intelligent agents such as robots and autonomous vehicles, since it enables them to anticipate and act early on time-critical incidents. State-of-the-art video prediction methods typically model the dynamics of a scene jointly and implicitly, without any explicit decomposition into separate objects. This is challenging and potentially sub-optimal, as every object in a dynamic scene has their own pattern of movement, typically somewhat independent of others. In this paper, we investigate the benefit of explicitly modeling the objects in a dynamic scene separately within the context of latent-transformer video prediction models. We conduct detailed and carefully-controlled experiments on both synthetic and real-world datasets; our results show that decomposing a dynamic scene leads to higher quality predictions compared with models of a similar capacity that lack such decomposition.
Related papers
- Pre-Trained Video Generative Models as World Simulators [59.546627730477454]
We propose Dynamic World Simulation (DWS) to transform pre-trained video generative models into controllable world simulators.
To achieve precise alignment between conditioned actions and generated visual changes, we introduce a lightweight, universal action-conditioned module.
Experiments demonstrate that DWS can be versatilely applied to both diffusion and autoregressive transformer models.
arXiv Detail & Related papers (2025-02-10T14:49:09Z) - InterDyn: Controllable Interactive Dynamics with Video Diffusion Models [50.38647583839384]
We propose InterDyn, a framework that generates videos of interactive dynamics given an initial frame and a control signal encoding the motion of a driving object or actor.
Our key insight is that large video foundation models can act as both neurals and implicit physics simulators by learning interactive dynamics from large-scale video data.
arXiv Detail & Related papers (2024-12-16T13:57:02Z) - Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback [130.090296560882]
We investigate the use of feedback to enhance the object dynamics in text-to-video models.
We show that our method can effectively optimize a wide variety of rewards, with binary AI feedback driving the most significant improvements in video quality for dynamic interactions.
arXiv Detail & Related papers (2024-12-03T17:44:23Z) - Predicting Long-horizon Futures by Conditioning on Geometry and Time [49.86180975196375]
We explore the task of generating future sensor observations conditioned on the past.
We leverage the large-scale pretraining of image diffusion models which can handle multi-modality.
We create a benchmark for video prediction on a diverse set of videos spanning indoor and outdoor scenes.
arXiv Detail & Related papers (2024-04-17T16:56:31Z) - Stochastic Video Prediction with Structure and Motion [14.424465835834042]
We propose to factorize video observations into static and dynamic components.
By learning separate distributions of changes in foreground and background, we can decompose the scene into static and dynamic parts.
Our experiments demonstrate that disentangling structure and motion helps video prediction, leading to better future predictions in complex driving scenarios.
arXiv Detail & Related papers (2022-03-20T11:29:46Z) - SLAMP: Stochastic Latent Appearance and Motion Prediction [14.257878210585014]
Motion is an important cue for video prediction and often utilized by separating video content into static and dynamic components.
Most of the previous work utilizing motion is deterministic but there are methods that can model the inherent uncertainty of the future.
In this paper, we reason about appearance and motion in the videoally by predicting the future based on the motion history.
arXiv Detail & Related papers (2021-08-05T17:52:18Z) - Dynamic View Synthesis from Dynamic Monocular Video [69.80425724448344]
We present an algorithm for generating views at arbitrary viewpoints and any input time step given a monocular video of a dynamic scene.
We show extensive quantitative and qualitative results of dynamic view synthesis from casually captured videos.
arXiv Detail & Related papers (2021-05-13T17:59:50Z) - Local Frequency Domain Transformer Networks for Video Prediction [24.126513851779936]
Video prediction is of interest not only in anticipating visual changes in the real world but has, above all, emerged as an unsupervised learning rule.
This paper proposes a fully differentiable building block that can perform all of those tasks separately while maintaining interpretability.
arXiv Detail & Related papers (2021-05-10T19:48:42Z) - Future Frame Prediction for Robot-assisted Surgery [57.18185972461453]
We propose a ternary prior guided variational autoencoder (TPG-VAE) model for future frame prediction in robotic surgical video sequences.
Besides content distribution, our model learns motion distribution, which is novel to handle the small movements of surgical tools.
arXiv Detail & Related papers (2021-03-18T15:12:06Z) - Unsupervised Video Decomposition using Spatio-temporal Iterative
Inference [31.97227651679233]
Multi-object scene decomposition is a fast-emerging problem in learning.
We show that our model has a high accuracy even without color information.
We demonstrate the decomposition, segmentation prediction capabilities of our model and show that it outperforms the state-of-the-art on several benchmark datasets.
arXiv Detail & Related papers (2020-06-25T22:57:17Z)
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.