Inferring Implicit 3D Representations from Human Figures on Pictorial Maps

• URL: http://arxiv.org/abs/2209.02385v2
• Date: Sat, 25 Mar 2023 17:44:40 GMT
• Title: Inferring Implicit 3D Representations from Human Figures on Pictorial Maps
• Authors: Raimund Schn\"urer, A. Cengiz \"Oztireli, Magnus Heitzler, Ren\'e Sieber, Lorenz Hurni
• Abstract summary: We present an automated workflow to bring human figures, one of the most frequently appearing entities on pictorial maps, to the third dimension. We first let a network consisting of fully connected layers estimate the depth coordinate of 2D pose points. The gained 3D pose points are inputted together with 2D masks of body parts into a deep implicit surface network to infer 3D signed distance fields.
• Score: 1.0499611180329804
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we present an automated workflow to bring human figures, one of the most frequently appearing entities on pictorial maps, to the third dimension. Our workflow is based on training data and neural networks for single-view 3D reconstruction of real humans from photos. We first let a network consisting of fully connected layers estimate the depth coordinate of 2D pose points. The gained 3D pose points are inputted together with 2D masks of body parts into a deep implicit surface network to infer 3D signed distance fields (SDFs). By assembling all body parts, we derive 2D depth images and body part masks of the whole figure for different views, which are fed into a fully convolutional network to predict UV images. These UV images and the texture for the given perspective are inserted into a generative network to inpaint the textures for the other views. The textures are enhanced by a cartoonization network and facial details are resynthesized by an autoencoder. Finally, the generated textures are assigned to the inferred body parts in a ray marcher. We test our workflow with 12 pictorial human figures after having validated several network configurations. The created 3D models look generally promising, especially when considering the challenges of silhouette-based 3D recovery and real-time rendering of the implicit SDFs. Further improvement is needed to reduce gaps between the body parts and to add pictorial details to the textures. Overall, the constructed figures may be used for animation and storytelling in digital 3D maps.

Related papers

• O$^2$-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model [28.372289119872764]
  Occlusion is a common issue in 3D reconstruction from RGB-D videos, often blocking the complete reconstruction of objects. We propose a novel framework, empowered by a 2D diffusion-based in-painting model, to reconstruct complete surfaces for the hidden parts of objects.
  arXiv  Detail & Related papers  (2023-08-18T14:38:31Z)
• ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections [71.46546520120162]
  Estimating 3D articulated shapes like animal bodies from monocular images is inherently challenging. We propose ARTIC3D, a self-supervised framework to reconstruct per-instance 3D shapes from a sparse image collection in-the-wild. We produce realistic animations by fine-tuning the rendered shape and texture under rigid part transformations.
  arXiv  Detail & Related papers  (2023-06-07T17:47:50Z)
• 3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping [37.14866512377012]
  3DHumanGAN is a 3D-aware generative adversarial network that synthesizes photorealistic images of full-body humans. We propose a novel generator architecture in which a 2D convolutional backbone is modulated by a 3D pose mapping network.
  arXiv  Detail & Related papers  (2022-12-14T17:59:03Z)
• TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network [14.389603490486364]
  Reconstructing 3D human body shapes from 3D partial textured scans is a fundamental task for many computer vision and graphics applications. We propose a new neural network architecture for 3D body shape and high-resolution texture completion.
  arXiv  Detail & Related papers  (2022-08-18T11:06:10Z)
• 3D-Aware Semantic-Guided Generative Model for Human Synthesis [67.86621343494998]
  This paper proposes a 3D-aware Semantic-Guided Generative Model (3D-SGAN) for human image synthesis. Our experiments on the DeepFashion dataset show that 3D-SGAN significantly outperforms the most recent baselines.
  arXiv  Detail & Related papers  (2021-12-02T17:10:53Z)
• Deep Hybrid Self-Prior for Full 3D Mesh Generation [57.78562932397173]
  We propose to exploit a novel hybrid 2D-3D self-prior in deep neural networks to significantly improve the geometry quality. In particular, we first generate an initial mesh using a 3D convolutional neural network with 3D self-prior, and then encode both 3D information and color information in the 2D UV atlas. Our method recovers the 3D textured mesh model of high quality from sparse input, and outperforms the state-of-the-art methods in terms of both the geometry and texture quality.
  arXiv  Detail & Related papers  (2021-08-18T07:44:21Z)
• D-OccNet: Detailed 3D Reconstruction Using Cross-Domain Learning [0.0]
  We extend the work on Occupancy Networks by exploiting cross-domain learning of image and point cloud domains. Our network, the Double Occupancy Network (D-OccNet) outperforms Occupancy Networks in terms of visual quality and details captured in the 3D reconstruction.
  arXiv  Detail & Related papers  (2021-04-28T16:00:54Z)
• NeuTex: Neural Texture Mapping for Volumetric Neural Rendering [48.83181790635772]
  We present an approach that explicitly disentangles geometry--represented as a continuous 3D volume--from appearance--represented as a continuous 2D texture map. We demonstrate that this representation can be reconstructed using only multi-view image supervision and generates high-quality rendering results.
  arXiv  Detail & Related papers  (2021-03-01T05:34:51Z)
• 3DBooSTeR: 3D Body Shape and Texture Recovery [76.91542440942189]
  3DBooSTeR is a novel method to recover a textured 3D body mesh from a partial 3D scan. The proposed approach decouples the shape and texture completion into two sequential tasks.
  arXiv  Detail & Related papers  (2020-10-23T21:07:59Z)
• Weakly Supervised Learning of Multi-Object 3D Scene Decompositions Using Deep Shape Priors [69.02332607843569]
  PriSMONet is a novel approach for learning Multi-Object 3D scene decomposition and representations from single images. A recurrent encoder regresses a latent representation of 3D shape, pose and texture of each object from an input RGB image. We evaluate the accuracy of our model in inferring 3D scene layout, demonstrate its generative capabilities, assess its generalization to real images, and point out benefits of the learned representation.
  arXiv  Detail & Related papers  (2020-10-08T14:49:23Z)

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.