3D Shape Reconstruction
55 papers with code • 2 benchmarks • 7 datasets
Pix3D
Hypersim
ApolloCar3D
4DFAB
HUMAN4D
FewSOL
Foot3D
Most implemented papers
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate.
Multi-Garment Net: Learning to Dress 3D People from Images
bharat-b7/MultiGarmentNetwork
•
•
ICCV 2019
We present Multi-Garment Network (MGN), a method to predict body shape and clothing, layered on top of the SMPL model from a few frames (1-8) of a video.
VIBE: Video Inference for Human Body Pose and Shape Estimation
Human motion is fundamental to understanding behavior.
TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style
chaitanya100100/TailorNet
•
•
CVPR 2020
While the low-frequency component is predicted from pose, shape and style parameters with an MLP, the high-frequency component is predicted with a mixture of shape-style specific pose models.
3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks
The decoder converts this representation into depth and normal maps capturing the underlying surface from several output viewpoints.
Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers
visinf/projects-2018-matryoshka
•
•
CVPR 2018
We scale this baseline to higher resolutions by proposing a memory-efficient shape encoding, which recursively decomposes a 3D shape into nested shape layers, similar to the pieces of a Matryoshka doll.
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization
facebookresearch/pifuhd
•
•
CVPR 2020
Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images.
The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction
rehg-lab/CLRec
•
•
Continual learning has been extensively studied for classification tasks with methods developed to primarily avoid catastrophic forgetting, a phenomenon where earlier learned concepts are forgotten at the expense of more recent samples.
CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation
This paper studies the complex task of simultaneous multi-object 3D reconstruction, 6D pose and size estimation from a single-view RGB-D observation.
Multi-modal 3D Shape Reconstruction Under Calibration Uncertainty using Parametric Level Set Methods
This method not only allows us to analytically and compactly represent the object, it also confers on us the ability to overcome calibration related noise that originates from inaccurate acquisition parameters.
