pvnieo/DPFM
Pytorch code for "DPFM: Deep Partial Functional Maps" - 3DV 2021 (Oral)
This tool helps researchers and engineers working with 3D models to automatically find correspondences between shapes, even when parts of one shape are missing or occluded. You provide a collection of 3D meshes and some examples of how points on these shapes map to each other, and it outputs a model that can predict these correspondences for new, incomplete 3D shapes. It's designed for professionals in computer graphics, vision, and related fields who analyze and compare 3D geometries.
No commits in the last 6 months.
Use this if you need to establish accurate point-to-point mappings between non-rigid 3D shapes where one or both shapes might have missing or partially occluded areas.
Not ideal if your task involves only complete 3D shapes or if you require mappings between entirely different object categories rather than variations of similar shapes.
Stars
42
Forks
4
Language
Python
License
GPL-3.0
Category
Last pushed
Aug 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/pvnieo/DPFM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
anchen1011/toflow
TOFlow: Video Enhancement with Task-Oriented Flow
NVlabs/nvdiffrec
Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and...
RuojinCai/doppelgangers
Doppelgangers: Learning to Disambiguate Images of Similar Structures
cvg/GlueStick
Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)
microsoft/SpareNet
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (CVPR 2021)