DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
- URL: http://arxiv.org/abs/2405.02280v2
- Date: Thu, 23 May 2024 16:27:11 GMT
- Title: DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
- Authors: Wen-Hsuan Chu, Lei Ke, Katerina Fragkiadaki,
- Abstract summary: We present DreamScene4D, the first approach to generate 3D dynamic scenes of multiple objects from monocular videos via novel view synthesis.
Our key insight is a "decompose-recompose" approach that factorizes the video scene into the background and object tracks.
We show extensive results on challenging DAVIS, Kubric, and self-captured videos with quantitative comparisons and a user preference study.
- Score: 21.93514516437402
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: View-predictive generative models provide strong priors for lifting object-centric images and videos into 3D and 4D through rendering and score distillation objectives. A question then remains: what about lifting complete multi-object dynamic scenes? There are two challenges in this direction: First, rendering error gradients are often insufficient to recover fast object motion, and second, view predictive generative models work much better for objects than whole scenes, so, score distillation objectives cannot currently be applied at the scene level directly. We present DreamScene4D, the first approach to generate 3D dynamic scenes of multiple objects from monocular videos via 360-degree novel view synthesis. Our key insight is a "decompose-recompose" approach that factorizes the video scene into the background and object tracks, while also factorizing object motion into 3 components: object-centric deformation, object-to-world-frame transformation, and camera motion. Such decomposition permits rendering error gradients and object view-predictive models to recover object 3D completions and deformations while bounding box tracks guide the large object movements in the scene. We show extensive results on challenging DAVIS, Kubric, and self-captured videos with quantitative comparisons and a user preference study. Besides 4D scene generation, DreamScene4D obtains accurate 2D persistent point track by projecting the inferred 3D trajectories to 2D. We will release our code and hope our work will stimulate more research on fine-grained 4D understanding from videos.
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) - DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and
Depth from Monocular Videos [76.01906393673897]
We propose a self-supervised method to jointly learn 3D motion and depth from monocular videos.
Our system contains a depth estimation module to predict depth, and a new decomposed object-wise 3D motion (DO3D) estimation module to predict ego-motion and 3D object motion.
Our model delivers superior performance in all evaluated settings.
arXiv Detail & Related papers (2024-03-09T12:22:46Z) - Tracking by 3D Model Estimation of Unknown Objects in Videos [122.56499878291916]
We argue that this representation is limited and instead propose to guide and improve 2D tracking with an explicit object representation.
Our representation tackles a complex long-term dense correspondence problem between all 3D points on the object for all video frames.
The proposed optimization minimizes a novel loss function to estimate the best 3D shape, texture, and 6DoF pose.
arXiv Detail & Related papers (2023-04-13T11:32:36Z) - Class-agnostic Reconstruction of Dynamic Objects from Videos [127.41336060616214]
We introduce REDO, a class-agnostic framework to REconstruct the Dynamic Objects from RGBD or calibrated videos.
We develop two novel modules. First, we introduce a canonical 4D implicit function which is pixel-aligned with aggregated temporal visual cues.
Second, we develop a 4D transformation module which captures object dynamics to support temporal propagation and aggregation.
arXiv Detail & Related papers (2021-12-03T18:57:47Z) - NeuralDiff: Segmenting 3D objects that move in egocentric videos [92.95176458079047]
We study the problem of decomposing the observed 3D scene into a static background and a dynamic foreground.
This task is reminiscent of the classic background subtraction problem, but is significantly harder because all parts of the scene, static and dynamic, generate a large apparent motion.
In particular, we consider egocentric videos and further separate the dynamic component into objects and the actor that observes and moves them.
arXiv Detail & Related papers (2021-10-19T12:51:35Z) - D3D-HOI: Dynamic 3D Human-Object Interactions from Videos [49.38319295373466]
We introduce D3D-HOI: a dataset of monocular videos with ground truth annotations of 3D object pose, shape and part motion during human-object interactions.
Our dataset consists of several common articulated objects captured from diverse real-world scenes and camera viewpoints.
We leverage the estimated 3D human pose for more accurate inference of the object spatial layout and dynamics.
arXiv Detail & Related papers (2021-08-19T00:49:01Z) - Unsupervised object-centric video generation and decomposition in 3D [36.08064849807464]
We propose to model a video as the view seen while moving through a scene with multiple 3D objects and a 3D background.
Our model is trained from monocular videos without any supervision, yet learns to generate coherent 3D scenes containing several moving objects.
arXiv Detail & Related papers (2020-07-07T18:01:29Z)
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.