MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering

• URL: http://arxiv.org/abs/2403.18820v2
• Date: Wed, 24 Jul 2024 16:04:02 GMT
• Title: MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering
• Authors: Guoxing Sun, Rishabh Dabral, Pascal Fua, Christian Theobalt, Marc Habermann,
• Abstract summary: We propose a method for efficient and high-quality geometry recovery and novel view synthesis given very sparse or even a single view of the human. Our key idea is to meta-learn the radiance field weights solely from potentially sparse multi-view videos. We collect a new dataset, WildDynaCap, which contains subjects captured in, both, a dense camera dome and in-the-wild sparse camera rigs.
• Score: 91.76893697171117
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Faithful human performance capture and free-view rendering from sparse RGB observations is a long-standing problem in Vision and Graphics. The main challenges are the lack of observations and the inherent ambiguities of the setting, e.g. occlusions and depth ambiguity. As a result, radiance fields, which have shown great promise in capturing high-frequency appearance and geometry details in dense setups, perform poorly when naively supervising them on sparse camera views, as the field simply overfits to the sparse-view inputs. To address this, we propose MetaCap, a method for efficient and high-quality geometry recovery and novel view synthesis given very sparse or even a single view of the human. Our key idea is to meta-learn the radiance field weights solely from potentially sparse multi-view videos, which can serve as a prior when fine-tuning them on sparse imagery depicting the human. This prior provides a good network weight initialization, thereby effectively addressing ambiguities in sparse-view capture. Due to the articulated structure of the human body and motion-induced surface deformations, learning such a prior is non-trivial. Therefore, we propose to meta-learn the field weights in a pose-canonicalized space, which reduces the spatial feature range and makes feature learning more effective. Consequently, one can fine-tune our field parameters to quickly generalize to unseen poses, novel illumination conditions as well as novel and sparse (even monocular) camera views. For evaluating our method under different scenarios, we collect a new dataset, WildDynaCap, which contains subjects captured in, both, a dense camera dome and in-the-wild sparse camera rigs, and demonstrate superior results compared to recent state-of-the-art methods on, both, public and WildDynaCap dataset.

Related papers

• FaVoR: Features via Voxel Rendering for Camera Relocalization [23.7893950095252]
  Camera relocalization methods range from dense image alignment to direct camera pose regression from a query image. We propose a novel approach that leverages a globally sparse yet locally dense 3D representation of 2D features. By tracking and triangulating landmarks over a sequence of frames, we construct a sparse voxel map optimized to render image patch descriptors observed during tracking.
  arXiv  Detail & Related papers  (2024-09-11T18:58:16Z)
• SPARF: Neural Radiance Fields from Sparse and Noisy Poses [58.528358231885846]
  We introduce Sparse Pose Adjusting Radiance Field (SPARF) to address the challenge of novel-view synthesis. Our approach exploits multi-view geometry constraints in order to jointly learn the NeRF and refine the camera poses.
  arXiv  Detail & Related papers  (2022-11-21T18:57:47Z)
• im2nerf: Image to Neural Radiance Field in the Wild [47.18702901448768]
  im2nerf is a learning framework that predicts a continuous neural object representation given a single input image in the wild. We show that im2nerf achieves the state-of-the-art performance for novel view synthesis from a single-view unposed image in the wild.
  arXiv  Detail & Related papers  (2022-09-08T23:28:56Z)
• CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations [77.90883737693325]
  This paper proposes CLONeR, which significantly improves upon NeRF by allowing it to model large outdoor driving scenes observed from sparse input sensor views. This is achieved by decoupling occupancy and color learning within the NeRF framework into separate Multi-Layer Perceptrons (MLPs) trained using LiDAR and camera data, respectively. In addition, this paper proposes a novel method to build differentiable 3D Occupancy Grid Maps (OGM) alongside the NeRF model, and leverage this occupancy grid for improved sampling of points along a ray for rendering in metric space.
  arXiv  Detail & Related papers  (2022-09-02T17:44:50Z)
• Neural Rendering of Humans in Novel View and Pose from Monocular Video [68.37767099240236]
  We introduce a new method that generates photo-realistic humans under novel views and poses given a monocular video as input. Our method significantly outperforms existing approaches under unseen poses and novel views given monocular videos as input.
  arXiv  Detail & Related papers  (2022-04-04T03:09:20Z)
• Dense Depth Priors for Neural Radiance Fields from Sparse Input Views [37.92064060160628]
  We propose a method to synthesize novel views of whole rooms from an order of magnitude fewer images. Our method enables data-efficient novel view synthesis on challenging indoor scenes, using as few as 18 images for an entire scene.
  arXiv  Detail & Related papers  (2021-12-06T19:00:02Z)
• DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras [63.186486240525554]
  DeepMultiCap is a novel method for multi-person performance capture using sparse multi-view cameras. Our method can capture time varying surface details without the need of using pre-scanned template models.
  arXiv  Detail & Related papers  (2021-05-01T14:32:13Z)
• Single View Metrology in the Wild [94.7005246862618]
  We present a novel approach to single view metrology that can recover the absolute scale of a scene represented by 3D heights of objects or camera height above the ground. Our method relies on data-driven priors learned by a deep network specifically designed to imbibe weakly supervised constraints from the interplay of the unknown camera with 3D entities such as object heights. We demonstrate state-of-the-art qualitative and quantitative results on several datasets as well as applications including virtual object insertion.
  arXiv  Detail & Related papers  (2020-07-18T22:31:33Z)

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.