DeepSDF is a deep learning framework for continuous 3D shape representation using Signed Distance Functions (SDFs), as presented in the CVPR 2019 paper DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation by Park et al. The framework learns a continuous implicit function that maps 3D coordinates to their corresponding signed distances from object surfaces, allowing compact, high-fidelity shape modeling. Unlike traditional discrete voxel grids or meshes, DeepSDF encodes shapes as continuous neural representations that can be smoothly interpolated and used for reconstruction, generation, and analysis. The repository provides complete tooling for preprocessing mesh datasets (e.g., ShapeNet), training DeepSDF models, reconstructing meshes from learned latent codes, and quantitatively evaluating results with metrics such as Chamfer Distance and Earth Mover’s Distance.
Features
- Learns continuous signed distance functions for compact 3D shape representation
- End-to-end training pipeline with configurable experiments and checkpoints
- Supports preprocessing, reconstruction, and evaluation for ShapeNet and other datasets
- Modular experiment directory structure for reproducibility and easy visualization
- Includes C++ utilities for mesh preprocessing and surface/SDF sampling
- Provides evaluation scripts for Chamfer and Earth Mover’s Distance metrics
Project Samples
