Instant Multi-View Head Capture through Learnable Registration

• URL: http://arxiv.org/abs/2306.07437v1
• Date: Mon, 12 Jun 2023 21:45:18 GMT
• Title: Instant Multi-View Head Capture through Learnable Registration
• Authors: Timo Bolkart and Tianye Li and Michael J. Black
• Abstract summary: Existing methods for capturing datasets of 3D heads in dense semantic correspondence are slow. We introduce TEMPEH to directly infer 3D heads in dense correspondence from calibrated multi-view images. Predicting one head takes about 0.3 seconds with a median reconstruction error of 0.26 mm, 64% lower than the current state-of-the-art.
• Score: 62.70443641907766
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing methods for capturing datasets of 3D heads in dense semantic correspondence are slow, and commonly address the problem in two separate steps; multi-view stereo (MVS) reconstruction followed by non-rigid registration. To simplify this process, we introduce TEMPEH (Towards Estimation of 3D Meshes from Performances of Expressive Heads) to directly infer 3D heads in dense correspondence from calibrated multi-view images. Registering datasets of 3D scans typically requires manual parameter tuning to find the right balance between accurately fitting the scans surfaces and being robust to scanning noise and outliers. Instead, we propose to jointly register a 3D head dataset while training TEMPEH. Specifically, during training we minimize a geometric loss commonly used for surface registration, effectively leveraging TEMPEH as a regularizer. Our multi-view head inference builds on a volumetric feature representation that samples and fuses features from each view using camera calibration information. To account for partial occlusions and a large capture volume that enables head movements, we use view- and surface-aware feature fusion, and a spatial transformer-based head localization module, respectively. We use raw MVS scans as supervision during training, but, once trained, TEMPEH directly predicts 3D heads in dense correspondence without requiring scans. Predicting one head takes about 0.3 seconds with a median reconstruction error of 0.26 mm, 64% lower than the current state-of-the-art. This enables the efficient capture of large datasets containing multiple people and diverse facial motions. Code, model, and data are publicly available at https://tempeh.is.tue.mpg.de.

Related papers

• GRAPE: Generalizable and Robust Multi-view Facial Capture [12.255610707737548]
  Deep learning-based multi-view facial capture methods have shown impressive accuracy while being several orders of magnitude faster than a traditional mesh registration pipeline. In this study, we aim to improve the generalization ability so that a trained model can be readily used for inference (i.e. capture new data) on a different camera array. Experiments on the FaMoS and FaceScape datasets demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-07-14T13:24:17Z)
• 3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features [70.50665869806188]
  3DiffTection is a state-of-the-art method for 3D object detection from single images. We fine-tune a diffusion model to perform novel view synthesis conditioned on a single image. We further train the model on target data with detection supervision.
  arXiv  Detail & Related papers  (2023-11-07T23:46:41Z)
• Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction [17.254539604491303]
  In this paper, we address the problem of few-shot full 3D head reconstruction. We accomplish this by incorporating a probabilistic shape and appearance prior into coordinate-based representations. We extend the H3DS dataset, which now comprises 60 high-resolution 3D full head scans and their corresponding posed images and masks.
  arXiv  Detail & Related papers  (2023-10-12T07:35:30Z)
• Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection [34.2238222373818]
  Current 3D object detection models follow a single dataset-specific training and testing paradigm. In this paper, we study the task of training a unified 3D detector from multiple datasets. We present a Uni3D which leverages a simple data-level correction operation and a designed semantic-level coupling-and-recoupling module.
  arXiv  Detail & Related papers  (2023-03-13T05:54:13Z)
• Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation [75.59415852802958]
  Shape-My-Face (SMF) is a powerful encoder-decoder architecture based on an improved point cloud encoder, a novel visual attention mechanism, graph convolutional decoders with skip connections, and a specialized mouth model. Our model provides topologically-sound meshes with minimal supervision, offers faster training time, has orders of magnitude fewer trainable parameters, is more robust to noise, and can generalize to previously unseen datasets.
  arXiv  Detail & Related papers  (2020-12-16T20:02:36Z)
• Reinforced Axial Refinement Network for Monocular 3D Object Detection [160.34246529816085]
  Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image. Conventional approaches sample 3D bounding boxes from the space and infer the relationship between the target object and each of them, however, the probability of effective samples is relatively small in the 3D space. We propose to start with an initial prediction and refine it gradually towards the ground truth, with only one 3d parameter changed in each step. This requires designing a policy which gets a reward after several steps, and thus we adopt reinforcement learning to optimize it.
  arXiv  Detail & Related papers  (2020-08-31T17:10:48Z)
• Monocular, One-stage, Regression of Multiple 3D People [105.3143785498094]
  We propose to Regress all meshes in a One-stage fashion for Multiple 3D People (termed ROMP) Our method simultaneously predicts a Body Center heatmap and a Mesh map, which can jointly describe the 3D body mesh on the pixel level. Compared with state-of-the-art methods, ROMP superior performance on the challenging multi-person benchmarks.
  arXiv  Detail & Related papers  (2020-08-27T17:21:47Z)
• Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation [57.11299763566534]
  We present a solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. We exploit 3D geometry to fuse input images into a unified latent representation of pose, which is disentangled from camera view-points. Our architecture then conditions the learned representation on camera projection operators to produce accurate per-view 2d detections.
  arXiv  Detail & Related papers  (2020-04-05T12:52:29Z)

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.