There are 2 repositories under single-view-reconstruction topic.
Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)
[ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
We evaluate our method on different datasets (including ShapeNet, CUB-200-2011, and Pascal3D+) and achieve state-of-the-art results, outperforming all the other supervised and unsupervised methods and 3D representations, all in terms of performance, accuracy, and training time.
Metrical Monocular Photometric Tracker [ECCV2022]
A diffuser implementation of Zero123. Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV23)
Topologically-Aware Deformation Fields for Single-View 3D Reconstruction (CVPR 2022)
Implementation of CVPR'23: Learning 3D Scene Priors with 2D Supervision
Code and datasets for TPAMI 2021 "SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images "
Neural Reflectance Field from Shading and Shadow under a Fixed Viewpoint
[AAAI 2023] Official implementation of "Occupancy Planes for Single-view RGB-D Human Reconstruction"
BuilDiff: 3D Building Shape Generation using Single-Image Conditional Point Cloud Diffusion Models
GAMesh: Guided and Augmented Meshing for Deep Point Networks
A new method to preprocess ShapeNet to get minimal shift 3D ground truth; 3 Stage single-view 3D reconstruction method; Point cloud surface reconstruction without input normals.
Python implementation of Single View Metrology using numpy and opencv
Pixel2point in PyTorch
Modular framework for experimenting with single-view voxel reconstruction, combined with domain adaptation.
Exploring the types of losses and decoder functions for regressing to voxels, point clouds, and mesh representations from single view RGB input.