FOUND: Foot Optimization with Uncertain Normals for Surface Deformation Using Synthetic Data
- URL: http://arxiv.org/abs/2310.18279v2
- Date: Thu, 22 Aug 2024 15:20:20 GMT
- Title: FOUND: Foot Optimization with Uncertain Normals for Surface Deformation Using Synthetic Data
- Authors: Oliver Boyne, Gwangbin Bae, James Charles, Roberto Cipolla,
- Abstract summary: We seek to develop a method for few-view reconstruction, for the case of the human foot.
To solve this task, we must extract rich geometric cues from RGB images, before carefully fusing them into a final 3D object.
We show that our normal predictor outperforms all off-the-shelf equivalents significantly on real images.
- Score: 27.53648027412686
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Surface reconstruction from multi-view images is a challenging task, with solutions often requiring a large number of sampled images with high overlap. We seek to develop a method for few-view reconstruction, for the case of the human foot. To solve this task, we must extract rich geometric cues from RGB images, before carefully fusing them into a final 3D object. Our FOUND approach tackles this, with 4 main contributions: (i) SynFoot, a synthetic dataset of 50,000 photorealistic foot images, paired with ground truth surface normals and keypoints; (ii) an uncertainty-aware surface normal predictor trained on our synthetic dataset; (iii) an optimization scheme for fitting a generative foot model to a series of images; and (iv) a benchmark dataset of calibrated images and high resolution ground truth geometry. We show that our normal predictor outperforms all off-the-shelf equivalents significantly on real images, and our optimization scheme outperforms state-of-the-art photogrammetry pipelines, especially for a few-view setting. We release our synthetic dataset and baseline 3D scans to the research community.
Related papers
- PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.
Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
arXiv Detail & Related papers (2024-10-29T15:28:15Z) - MS-PS: A Multi-Scale Network for Photometric Stereo With a New
Comprehensive Training Dataset [0.0]
Photometric stereo (PS) problem consists in reconstructing the 3D-surface of an object.
We propose a multi-scale architecture for PS which, combined with a new dataset, yields state-of-the-art results.
arXiv Detail & Related papers (2022-11-25T14:01:54Z) - Shape, Pose, and Appearance from a Single Image via Bootstrapped
Radiance Field Inversion [54.151979979158085]
We introduce a principled end-to-end reconstruction framework for natural images, where accurate ground-truth poses are not available.
We leverage an unconditional 3D-aware generator, to which we apply a hybrid inversion scheme where a model produces a first guess of the solution.
Our framework can de-render an image in as few as 10 steps, enabling its use in practical scenarios.
arXiv Detail & Related papers (2022-11-21T17:42:42Z) - Simple and Effective Synthesis of Indoor 3D Scenes [78.95697556834536]
We study the problem of immersive 3D indoor scenes from one or more images.
Our aim is to generate high-resolution images and videos from novel viewpoints.
We propose an image-to-image GAN that maps directly from reprojections of incomplete point clouds to full high-resolution RGB-D images.
arXiv Detail & Related papers (2022-04-06T17:54:46Z) - Adversarial Parametric Pose Prior [106.12437086990853]
We learn a prior that restricts the SMPL parameters to values that produce realistic poses via adversarial training.
We show that our learned prior covers the diversity of the real-data distribution, facilitates optimization for 3D reconstruction from 2D keypoints, and yields better pose estimates when used for regression from images.
arXiv Detail & Related papers (2021-12-08T10:05:32Z) - UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body
Decoupling 3D Model [58.70130563417079]
We introduce a new 3D human-body model with a series of decoupled parameters that could freely control the generation of the body.
Compared to the existing manually annotated DensePose-COCO dataset, the synthetic UltraPose has ultra dense image-to-surface correspondences without annotation cost and error.
arXiv Detail & Related papers (2021-10-28T16:24:55Z) - SIDER: Single-Image Neural Optimization for Facial Geometric Detail
Recovery [54.64663713249079]
SIDER is a novel photometric optimization method that recovers detailed facial geometry from a single image in an unsupervised manner.
In contrast to prior work, SIDER does not rely on any dataset priors and does not require additional supervision from multiple views, lighting changes or ground truth 3D shape.
arXiv Detail & Related papers (2021-08-11T22:34:53Z) - Hybrid Approach for 3D Head Reconstruction: Using Neural Networks and
Visual Geometry [3.970492757288025]
We present a novel method for reconstructing 3D heads from a single or multiple image(s) using a hybrid approach based on deep learning and geometric techniques.
We propose an encoder-decoder network based on the U-net architecture and trained on synthetic data only.
arXiv Detail & Related papers (2021-04-28T11:31:35Z) - SimPose: Effectively Learning DensePose and Surface Normals of People
from Simulated Data [7.053519629075887]
We present a technique for learning difficult per-pixel 2.5D and 3D regression representations of articulated people.
We obtained strong sim-to-real domain generalization for the 2.5DPose estimation task and the 3D human surface normal estimation task.
Our approach is complementary to existing domain-adaptation techniques and can be applied to other dense per-pixel pose estimation problems.
arXiv Detail & Related papers (2020-07-30T14:59:38Z) - Photometric Multi-View Mesh Refinement for High-Resolution Satellite
Images [24.245977127434212]
State-of-the-art reconstruction methods typically generate 2.5D elevation data.
We present an approach to recover full 3D surface meshes from multi-view satellite imagery.
arXiv Detail & Related papers (2020-05-10T20:37:54Z)
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.