SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes

• URL: http://arxiv.org/abs/2308.10638v2
• Date: Mon, 6 May 2024 16:14:23 GMT
• Title: SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes
• Authors: Soubhik Sanyal, Partha Ghosh, Jinlong Yang, Michael J. Black, Justus Thies, Timo Bolkart,
• Abstract summary: We present SCULPT, a novel 3D generative model for clothed and textured 3D meshes of humans. We devise a deep neural network that learns to represent the geometry and appearance distribution of clothed human bodies.
• Score: 62.82552328188602
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present SCULPT, a novel 3D generative model for clothed and textured 3D meshes of humans. Specifically, we devise a deep neural network that learns to represent the geometry and appearance distribution of clothed human bodies. Training such a model is challenging, as datasets of textured 3D meshes for humans are limited in size and accessibility. Our key observation is that there exist medium-sized 3D scan datasets like CAPE, as well as large-scale 2D image datasets of clothed humans and multiple appearances can be mapped to a single geometry. To effectively learn from the two data modalities, we propose an unpaired learning procedure for pose-dependent clothed and textured human meshes. Specifically, we learn a pose-dependent geometry space from 3D scan data. We represent this as per vertex displacements w.r.t. the SMPL model. Next, we train a geometry conditioned texture generator in an unsupervised way using the 2D image data. We use intermediate activations of the learned geometry model to condition our texture generator. To alleviate entanglement between pose and clothing type, and pose and clothing appearance, we condition both the texture and geometry generators with attribute labels such as clothing types for the geometry, and clothing colors for the texture generator. We automatically generated these conditioning labels for the 2D images based on the visual question answering model BLIP and CLIP. We validate our method on the SCULPT dataset, and compare to state-of-the-art 3D generative models for clothed human bodies. Our code and data can be found at https://sculpt.is.tue.mpg.de.

Related papers

• FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesis [51.193297565630886]
  The challenge of accurately inferring texture remains, particularly in obscured areas such as the back of a person in frontal-view images. This limitation in texture prediction largely stems from the scarcity of large-scale and diverse 3D datasets. We propose leveraging extensive 2D fashion datasets to enhance both texture and shape prediction in 3D human digitization.
  arXiv  Detail & Related papers  (2024-10-13T01:25:05Z)
• AG3D: Learning to Generate 3D Avatars from 2D Image Collections [96.28021214088746]
  We propose a new adversarial generative model of realistic 3D people from 2D images. Our method captures shape and deformation of the body and loose clothing by adopting a holistic 3D generator. We experimentally find that our method outperforms previous 3D- and articulation-aware methods in terms of geometry and appearance.
  arXiv  Detail & Related papers  (2023-05-03T17:56:24Z)
• Accurate 3D Body Shape Regression using Metric and Semantic Attributes [55.58629009876271]
  We show that 3D body shape regression from images can be trained from easy-to-obtain anthropometric measurements and linguistic shape attributes. This is the first demonstration that 3D body shape regression from images can be trained from easy-to-obtain anthropometric measurements and linguistic shape attributes.
  arXiv  Detail & Related papers  (2022-06-14T17:54:49Z)
• The Power of Points for Modeling Humans in Clothing [60.00557674969284]
  Currently it requires an artist to create 3D human avatars with realistic clothing that can move naturally. We show that a 3D representation can capture varied topology at high resolution and that can be learned from data. We train a neural network with a novel local clothing geometric feature to represent the shape of different outfits.
  arXiv  Detail & Related papers  (2021-09-02T17:58:45Z)
• Leveraging 2D Data to Learn Textured 3D Mesh Generation [33.32377849866736]
  We present the first generative model of textured 3D meshes. We train our model to explain a distribution of images by modelling each image as a 3D foreground object. It learns to generate meshes that when rendered, produce images similar to those in its training set.
  arXiv  Detail & Related papers  (2020-04-08T18:00:37Z)
• Learning to Transfer Texture from Clothing Images to 3D Humans [50.838970996234465]
  We present a method to automatically transfer textures of clothing images to 3D garments worn on top SMPL, in real time. We first compute training pairs of images with aligned 3D garments using a custom non-rigid 3D to 2D registration method, which is accurate but slow. Our model opens the door to applications such as virtual try-on, and allows for generation of 3D humans with varied textures which is necessary for learning.
  arXiv  Detail & Related papers  (2020-03-04T12:53:58Z)

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.