multi-view-reconstruction

A Unified Framework for Surface Reconstruction

A Modular Framework for 3D Gaussian Splatting and Beyond

[NeurIPS 2023] Official code of "One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization"

[NeurIPS'22] MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces (CVPR 2023)

HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details (NeurIPS 2022)

[AAAI'24] NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views

[CVPR 2023] Multi-View Azimuth Stereo via Tangent Space Consistency

Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025)

(PG2023/CGF) This is the official PyTorch implementation of PG2023/CGF paper: GA-Sketching: Shape Modeling from Multi-View Sketching with Geometry-Aligned Deep Implicit Functions

[IJCAI 2025] Optimized View and Geometry Distillation from Multi-view Diffuser

High-Fidelity 3D Reconstruction via Graph Optimization. A Multi-Frame Registration and reconstruction algorithm.

Actively maintained fork of SDFStudio: Neural implicit surface reconstruction with modern PyTorch, RTX 40XX support, PBR exports, and bug fixes

A lightweight neural network for multi-view classification and reconstruction.

A novel hybrid architecture combining CNNs and Swin Transformers, to address limitations in 3D voxel reconstruction.

A unified, feed-forward model integrating the MapAnything 3D reconstruction backbone with Mask2Former for multi-view consistent panoptic segmentation. This approach provides feature-rich and metric accurate semantic maps for indoor robot navigation while eliminating the need for posed inputs and costly test-time optimization.

Multi-View RGB-based Recognition and Reconstruction in PyTorch

Short-window synchronized multi-view camera pose and 4D reconstruction with VGGT-Omega