Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-5

3D Shape Modeling

3260 papers • 126 benchmarks • 313 datasets

Image: Gkioxari et al

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in 3d-shape-modeling-5

Trend

Dataset

Best Model

Actions

Pix3D S2

Pix3D S1

Libraries

Use these libraries to find 3d-shape-modeling-5 models and implementations

Datasets

Pix3D

Subtasks

No subtasks available.

Most implemented papers

Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling

Jiajun Wu, J. Tenenbaum, W. Freeman, Tianfan Xue, Xingyuan Sun, Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang•Wed Apr 11 2018

A novel model is designed that simultaneously performs 3D reconstruction and pose estimation; this multi-task learning approach achieves state-of-the-art performance on both tasks.

499

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Learning to Dress 3D People in Generative Clothing

Michael J. Black, Siyu Tang, Gerard Pons-Moll, S. Pujades, Anurag Ranjan, Qianli Ma, Jinlong Yang•Tue Jul 30 2019

Three-dimensional human body models are widely used in the analysis of human pose and motion. Existing models, however, are learned from minimally-clothed 3D scans and thus do not generalize to the complexity of dressed people in common images and videos. Additionally, current models lack the expressive power needed to represent the complex non-linear geometry of pose-dependent clothing shapes. To address this, we learn a generative 3D mesh model of clothed people from 3D scans with varying pose and clothing. Specifically, we train a conditional Mesh-VAE-GAN to learn the clothing deformation from the SMPL body model, making clothing an additional term in SMPL. Our model is conditioned on both pose and clothing type, giving the ability to draw samples of clothing to dress different body shapes in a variety of styles and poses. To preserve wrinkle detail, our Mesh-VAE-GAN extends patchwise discriminators to 3D meshes. Our model, named CAPE, represents global shape and fine local structure, effectively extending the SMPL body model to clothing. To our knowledge, this is the first generative model that directly dresses 3D human body meshes and generalizes to different poses. The model, code and data are available for research purposes at https://cape.is.tue.mpg.de.

397 0

Paper Graph

GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision

Yu-Wing Tai, Chi-Keung Tang, Lei Ke, Yanan Sun, Shichao Li•Sat Jul 25 2020

A novel end-to-end framework named GSNet (Geometric and Scene-aware Network), which jointly estimates 6DoF poses and reconstructs detailed 3D car shapes from single urban street view, and inspires a new multi-objective loss function to regularize network training.

54 0

Paper Graph

Object Shape Error Response Using Bayesian 3-D Convolutional Neural Networks for Assembly Systems With Compliant Parts

S. Sinha, P. Franciosa, D. Ceglarek•Mon Dec 07 2020

The OSER approach leverages Bayesian 3-D convolutional neural networks integrated with computer-aided engineering simulations for RC isolation to estimate the dimensional and geometric variation of assembled products and then, relate these to process parameters, which can be interpreted as root causes of the object shape defects.

8 0

Paper Graph

3DILG: Irregular Latent Grids for 3D Generative Modeling

M. Nießner, Peter Wonka, Biao Zhang•Thu May 26 2022

In the context of shape reconstruction from point clouds, the shape representation built on irregular grids improves upon grid-based methods in terms of reconstruction accuracy and promotes high-quality shape generation using auto-regressive probabilistic models.

100 0

Paper Graph

LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling

Yinda Zhang, Yanwei Fu, Boyan Jiang, Xinlin Ren, Mingsong Dou, Xiangyang Xue•Wed Aug 17 2022

This paper proposes a novel Local 4D implicit Representation for Dynamic clothed human, named LoRD, which has the merits of both 4D human modeling and local representation, and enables high-fidelity reconstruction with detailed surface deformations, such as clothing wrinkles.

10 0

Paper Graph

3D VR Sketch Guided 3D Shape Prototyping and Exploration

Ling Luo, Yulia Gryaditskaya, Yi-Zhe Song, Pinaki Nath Chowdhury, Tao Xiang•Sun Jun 18 2023

A 3D shape generation network that takes a 3D VR sketch as a condition, assuming that sketches are created by novices without art training and aim to reconstruct geometrically realistic 3D shapes of a given category is proposed.

17 0

Paper Graph

Adding a benchmark result helps the community track progress.

3D Shape Modeling | State-of-the-Art