MachinePerceptionLab/Attentive_DFPrior
[NeurIPS'23] Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priors
This project helps computer vision researchers and 3D reconstruction specialists create highly accurate 3D models of real-world scenes. It takes in a series of color and depth images (like those captured by a 3D scanner) and outputs a detailed 3D mesh model of the environment. The result is a precise digital representation of a physical space, useful for various analytical and visualization tasks.
No commits in the last 6 months.
Use this if you need to reconstruct complex 3D scenes from depth and color camera feeds, achieving state-of-the-art accuracy, especially for real-time applications or detailed environmental mapping.
Not ideal if you're looking for a simple, out-of-the-box solution for basic object scanning or if you don't have access to detailed color and depth input data.
Stars
27
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jun 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/MachinePerceptionLab/Attentive_DFPrior"
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)