List.md

Paper List

• 1 3dr2n2: A unified approach for single and multi-view 3d object Reconstruction

• 2 Learning a predictable and generative vector representation for objects

• 3 Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling

• 4 Perspective transformer nets: Learning single-view 3d object reconstruction without 3d supervision

• 5 [Deep disentangled representations for volumetric reconstruction]

• 6 Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs

• 7 Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency

• 8 Learning a Hierarchical Latent-Variable Model of 3D Shapes

• 9 Weakly-Supervised Generative Adversarial Networks for 3D Reconstruction (Weakly Supervised 3D Reconstruction with Adversarial Constraint)

• 10 [Rethinking Reprojection: Closing the Loop for Pose-aware Shape Reconstruction from a Single Image]

• 11 [Scaling CNNs for High Resolution Volumetric Reconstruction From a Single Image]

• 12 [Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55]

• 13 A Point Set Generation Network for 3D Object Reconstruction from a Single Image

• 14 Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction

• 15 DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image

• 16 Neural 3D Mesh Renderer

• 17 Image2Mesh: A Learning Framework for Single Image 3DReconstruction

• 18 SurfNet: Generating 3D shape surfaces using deep residual networks

• 19 Hierarchical Surface Prediction for 3D Object Reconstruction

• 20 Multi-view 3D Models from Single Images with a Convolutional Network

• 21 Single Image 3D Interpreter Network

• 22 Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction

• 23 AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation

• 24 Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images

• 25 Multiresolution Tree Networks for 3D Point Cloud Processing

• 26 O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis

• 27 Learning Implicit Fields for Generative Shape Modeling

• 28 Occupancy Networks: Learning 3D Reconstruction in Function Space

• 29 DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation