Browse SoTA > Computer Vision > 3D > 3D Shape Reconstruction

3D Shape Reconstruction

19 papers with code · Computer Vision
Subtask of 3D

Image: Pix3D

Benchmarks

Greatest papers with code

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

CVPR 2020 facebookresearch/pifuhd

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.

3D HUMAN POSE ESTIMATION 3D OBJECT RECONSTRUCTION FROM A SINGLE IMAGE 3D SHAPE RECONSTRUCTION

Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55

17 Oct 2017facebookresearch/SparseConvNet

We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.

3D PART SEGMENTATION 3D RECONSTRUCTION 3D SHAPE RECONSTRUCTION

PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization

ICCV 2019 shunsukesaito/PIFu

We introduce Pixel-aligned Implicit Function (PIFu), a highly effective implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object.

3D HUMAN POSE ESTIMATION 3D OBJECT RECONSTRUCTION FROM A SINGLE IMAGE 3D SHAPE RECONSTRUCTION FROM A SINGLE 2D IMAGE

Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion

CVPR 2020 autonomousvision/convolutional_occupancy_networks

To solve this, we propose Implicit Feature Networks (IF-Nets), which deliver continuous outputs, can handle multiple topologies, and complete shapes for missing or sparse input data retaining the nice properties of recent learned implicit functions, but critically they can also retain detail when it is present in the input data, and can reconstruct articulated humans.

3D OBJECT RECONSTRUCTION 3D RECONSTRUCTION 3D SHAPE RECONSTRUCTION

Multi-Garment Net: Learning to Dress 3D People from Images

ICCV 2019 bharat-b7/MultiGarmentNetwork

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.

3D HUMAN POSE ESTIMATION 3D SHAPE RECONSTRUCTION FROM A SINGLE 2D IMAGE

TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style

CVPR 2020 chaitanya100100/TailorNet

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 HUMAN POSE ESTIMATION 3D SHAPE RECONSTRUCTION

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

ECCV 2020 facebookresearch/phosa

We present a method that infers spatial arrangements and shapes of humans and objects in a globally consistent 3D scene, all from a single image in-the-wild captured in an uncontrolled environment.

3D HUMAN POSE ESTIMATION 3D SHAPE RECONSTRUCTION FROM A SINGLE 2D IMAGE COMMON SENSE REASONING HUMAN-OBJECT INTERACTION DETECTION

SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator

13 Nov 2019sw-gong/spiralnet_plus

Intrinsic graph convolution operators with differentiable kernel functions play a crucial role in analyzing 3D shape meshes.

3D SHAPE RECONSTRUCTION