SketchBodyNet: A Sketch-Driven Multi-faceted Decoder Network for 3D Human Reconstruction

• URL: http://arxiv.org/abs/2310.06577v1
• Date: Tue, 10 Oct 2023 12:38:34 GMT
• Title: SketchBodyNet: A Sketch-Driven Multi-faceted Decoder Network for 3D Human Reconstruction
• Authors: Fei Wang, Kongzhang Tang, Hefeng Wu, Baoquan Zhao, Hao Cai, Teng Zhou
• Abstract summary: We propose a sketch-driven multi-faceted decoder network termed SketchBodyNet to address this task. Our network achieves superior performance in reconstructing 3D human meshes from freehand sketches.
• Score: 18.443079472919635
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reconstructing 3D human shapes from 2D images has received increasing attention recently due to its fundamental support for many high-level 3D applications. Compared with natural images, freehand sketches are much more flexible to depict various shapes, providing a high potential and valuable way for 3D human reconstruction. However, such a task is highly challenging. The sparse abstract characteristics of sketches add severe difficulties, such as arbitrariness, inaccuracy, and lacking image details, to the already badly ill-posed problem of 2D-to-3D reconstruction. Although current methods have achieved great success in reconstructing 3D human bodies from a single-view image, they do not work well on freehand sketches. In this paper, we propose a novel sketch-driven multi-faceted decoder network termed SketchBodyNet to address this task. Specifically, the network consists of a backbone and three separate attention decoder branches, where a multi-head self-attention module is exploited in each decoder to obtain enhanced features, followed by a multi-layer perceptron. The multi-faceted decoders aim to predict the camera, shape, and pose parameters, respectively, which are then associated with the SMPL model to reconstruct the corresponding 3D human mesh. In learning, existing 3D meshes are projected via the camera parameters into 2D synthetic sketches with joints, which are combined with the freehand sketches to optimize the model. To verify our method, we collect a large-scale dataset of about 26k freehand sketches and their corresponding 3D meshes containing various poses of human bodies from 14 different angles. Extensive experimental results demonstrate our SketchBodyNet achieves superior performance in reconstructing 3D human meshes from freehand sketches.

Related papers

• Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering [17.918603435615335]
  3D sketches are widely used for visually representing the 3D shape and structure of objects or scenes. We propose Diff3DS, a novel differentiable framework for generating view-consistent 3D sketch. Our framework bridges the domains of 3D sketch and customized image, achieving end-toend optimization of 3D sketch.
  arXiv  Detail & Related papers  (2024-05-24T07:48:14Z)
• En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data [36.51674664590734]
  We present En3D, an enhanced izable scheme for high-qualityd 3D human avatars. Unlike previous works that rely on scarce 3D datasets or limited 2D collections with imbalance viewing angles and pose priors, our approach aims to develop a zero-shot 3D capable of producing 3D humans.
  arXiv  Detail & Related papers  (2024-01-02T12:06:31Z)
• SHERF: Generalizable Human NeRF from a Single Image [59.10589479808622]
  SHERF is the first generalizable Human NeRF model for recovering animatable 3D humans from a single input image. We propose a bank of 3D-aware hierarchical features, including global, point-level, and pixel-aligned features, to facilitate informative encoding.
  arXiv  Detail & Related papers  (2023-03-22T17:59:12Z)
• 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)
• Interactive Sketching of Mannequin Poses [3.222802562733787]
  3D body poses are necessary for various downstream applications. We propose a machine-learning model for inferring the 3D pose of a CG mannequin from sketches of humans drawn in a cylinder-person style. Our unique approach to vector graphics training data underpins our integrated ML-and-kinematics system.
  arXiv  Detail & Related papers  (2022-12-14T08:45:51Z)
• GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images [72.15855070133425]
  We introduce GET3D, a Generative model that directly generates Explicit Textured 3D meshes with complex topology, rich geometric details, and high-fidelity textures. GET3D is able to generate high-quality 3D textured meshes, ranging from cars, chairs, animals, motorbikes and human characters to buildings.
  arXiv  Detail & Related papers  (2022-09-22T17:16:19Z)
• Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape [77.95154911528365]
  3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori. Previous reconstructed 3D faces suffer from degraded visual verisimilitude due to the loss of fine-grained geometry. This paper proposes a complete solution to capture the personalized shape so that the reconstructed shape looks identical to the corresponding person.
  arXiv  Detail & Related papers  (2022-04-09T03:46:18Z)
• Gait Recognition in the Wild with Dense 3D Representations and A Benchmark [86.68648536257588]
  Existing studies for gait recognition are dominated by 2D representations like the silhouette or skeleton of the human body in constrained scenes. This paper aims to explore dense 3D representations for gait recognition in the wild. We build the first large-scale 3D representation-based gait recognition dataset, named Gait3D.
  arXiv  Detail & Related papers  (2022-04-06T03:54:06Z)
• DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars [92.37436369781692]
  We present DRaCoN, a framework for learning full-body volumetric avatars. It exploits the advantages of both the 2D and 3D neural rendering techniques. Experiments on the challenging ZJU-MoCap and Human3.6M datasets indicate that DRaCoN outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-03-29T17:59:15Z)
• 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)
• 3D Shape Reconstruction from Free-Hand Sketches [42.15888734492648]
  Despite great progress achieved in 3D reconstruction from distortion-free line drawings, little effort has been made to reconstruct 3D shapes from free-hand sketches. We aim to enhance the power of sketches in 3D-related applications such as interactive design and VR/AR games. A major challenge for free-hand sketch 3D reconstruction comes from the insufficient training data and free-hand sketch diversity.
  arXiv  Detail & Related papers  (2020-06-17T07:43:10Z)

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.