SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes

• URL: http://arxiv.org/abs/2308.08258v1
• Date: Wed, 16 Aug 2023 09:50:35 GMT
• Title: SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes
• Authors: Edith Tretschk, Vladislav Golyanik, Michael Zollhoefer, Aljaz Bozic, Christoph Lassner, Christian Theobalt
• Abstract summary: We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner. Our method takes multi-view RGB videos and background images from static cameras with known camera parameters as input. We show experimentally that, unlike prior work that only handles small motion, our method enables the reconstruction of studio-scale motions.
• Score: 75.9110646062442
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing methods for the 4D reconstruction of general, non-rigidly deforming objects focus on novel-view synthesis and neglect correspondences. However, time consistency enables advanced downstream tasks like 3D editing, motion analysis, or virtual-asset creation. We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner. Our dynamic-NeRF method takes multi-view RGB videos and background images from static cameras with known camera parameters as input. It then reconstructs the deformations of an estimated canonical model of the geometry and appearance in an online fashion. Since this canonical model is time-invariant, we obtain correspondences even for long-term, long-range motions. We employ neural scene representations to parametrize the components of our method. Like prior dynamic-NeRF methods, we use a backwards deformation model. We find non-trivial adaptations of this model necessary to handle larger motions: We decompose the deformations into a strongly regularized coarse component and a weakly regularized fine component, where the coarse component also extends the deformation field into the space surrounding the object, which enables tracking over time. We show experimentally that, unlike prior work that only handles small motion, our method enables the reconstruction of studio-scale motions.

Related papers

• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion [118.74385965694694]
  We present Motion DUSt3R (MonST3R), a novel geometry-first approach that directly estimates per-timestep geometry from dynamic scenes. By simply estimating a pointmap for each timestep, we can effectively adapt DUST3R's representation, previously only used for static scenes, to dynamic scenes. We show that by posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics.
  arXiv  Detail & Related papers  (2024-10-04T18:00:07Z)
• TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene [25.164085646259856]
  This paper introduces a 3D semantic NeRF for dynamic scenes captured from sparse or singleview RGB videos. Our framework uses an Invertible Neural Network (INN) for LBS prediction, the training process. Our approach produces high-quality reconstructions of both deformable and non-deformable objects in complex interactions.
  arXiv  Detail & Related papers  (2024-09-26T01:34:42Z)
• CRiM-GS: Continuous Rigid Motion-Aware Gaussian Splatting from Motion Blur Images [12.603775893040972]
  We propose continuous rigid motion-aware gaussian splatting (CRiM-GS) to reconstruct accurate 3D scene from blurry images with real-time rendering speed. We leverage rigid body transformations to model the camera motion with proper regularization, preserving the shape and size of the object. Furthermore, we introduce a continuous deformable 3D transformation in the textitSE(3) field to adapt the rigid body transformation to real-world problems.
  arXiv  Detail & Related papers  (2024-07-04T13:37:04Z)
• Diffusion Priors for Dynamic View Synthesis from Monocular Videos [59.42406064983643]
  Dynamic novel view synthesis aims to capture the temporal evolution of visual content within videos. We first finetune a pretrained RGB-D diffusion model on the video frames using a customization technique. We distill the knowledge from the finetuned model to a 4D representations encompassing both dynamic and static Neural Radiance Fields.
  arXiv  Detail & Related papers  (2024-01-10T23:26:41Z)
• Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models [4.529832252085145]
  We propose a novel SfT reconstruction algorithm for cloth using a pre-trained neural surrogate model. Differentiable rendering of the simulated mesh enables pixel-wise comparisons between the reconstruction and a target video sequence. This allows to retain a precise, stable, and smooth reconstructed geometry while reducing the runtime by a factor of 400-500 compared to $phi$-SfT.
  arXiv  Detail & Related papers  (2023-11-21T18:59:58Z)
• Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting [8.078460597825142]
  Reconstructing dynamic 3D scenes from 2D images and generating diverse views over time is challenging due to scene complexity and temporal dynamics. We propose to approximate the underlying-temporal rendering volume of a dynamic scene by optimizing a collection of 4D primitives, with explicit geometry and appearance modeling. Our model is conceptually simple, consisting of a 4D Gaussian parameterized by anisotropic ellipses that can rotate arbitrarily in space and time, as well as view-dependent and time-evolved appearance represented by the coefficient of 4D spherindrical harmonics.
  arXiv  Detail & Related papers  (2023-10-16T17:57:43Z)
• NeuPhysics: Editable Neural Geometry and Physics from Monocular Videos [82.74918564737591]
  We present a method for learning 3D geometry and physics parameters of a dynamic scene from only a monocular RGB video input. Experiments show that our method achieves superior mesh and video reconstruction of dynamic scenes compared to competing Neural Field approaches.
  arXiv  Detail & Related papers  (2022-10-22T04:57:55Z)
• Learning Dynamic View Synthesis With Few RGBD Cameras [60.36357774688289]
  We propose to utilize RGBD cameras to synthesize free-viewpoint videos of dynamic indoor scenes. We generate point clouds from RGBD frames and then render them into free-viewpoint videos via a neural feature. We introduce a simple Regional Depth-Inpainting module that adaptively inpaints missing depth values to render complete novel views.
  arXiv  Detail & Related papers  (2022-04-22T03:17:35Z)
• MoCo-Flow: Neural Motion Consensus Flow for Dynamic Humans in Stationary Monocular Cameras [98.40768911788854]
  We introduce MoCo-Flow, a representation that models the dynamic scene using a 4D continuous time-variant function. At the heart of our work lies a novel optimization formulation, which is constrained by a motion consensus regularization on the motion flow. We extensively evaluate MoCo-Flow on several datasets that contain human motions of varying complexity.
  arXiv  Detail & Related papers  (2021-06-08T16:03:50Z)

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.