Reconstruction
[CVPR'20] SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
[AAAI'24] NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views
Python implementation of Visual Odometry algorithms from http://rpg.ifi.uzh.ch/
[TPAMI'2024 / NeurIPS'2022]: CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization
A Unified Framework for Surface Reconstruction
[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
A Framework for the Volumetric Integration of Depth Images
Calculate signed distance fields for arbitrary meshes
A GPU-accelerated TSDF and ESDF library for robots equipped with RGB-D cameras.
[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
Parallelized triangle mesh --> continuous signed distance field on CPU
Volumetric structures such as voxels and SDFs implemented in pytorch
Pytorch code for ECCV'22 paper. ShAPO: Implicit Representations for Multi-Object Shape, Appearance and Pose Optimization
SfM-Free 3D Gaussian Splatting via Hierarchical Training
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Official implementation of On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images. A. Meuleman, I. Shah, A. Lanvin, B. Kerbl, G. Drettakis, ACM TOG (proc. SIGGRAPH) 2025
[3DV 2025 Best Paper] We present Object Images (Omages): An homage to the classic Geometry Images.