nas3r
Research code for a self-supervised method that reconstructs 3D scenes from images without camera poses or prior 3D data. It accompanies a CVPR 2026 paper.
Share on XLicense: MIT
Overview
NAS3R is research code from a CVPR 2026 paper on reconstructing 3D scenes from ordinary images. It is a self-supervised, feed-forward framework that learns 3D geometry and camera parameters together, without ground-truth annotations or pretrained priors. The repository provides installation steps, checkpoints hosted on Hugging Face, and instructions for datasets, training and evaluation in Python with PyTorch.
Key features
- Learns 3D geometry and camera parameters jointly
- Needs no ground-truth labels or pretrained priors
- Checkpoints for two-view and multi-view models on Hugging Face
- Optional camera intrinsics input for some checkpoints
- VGGT-based and MASt3R-style architecture variants
Best for
Researchers working on pose-free 3D reconstruction or novel view synthesis who want to reproduce or build on the paper. It is research code that expects a CUDA PyTorch setup.
- Upstream
- ranrhuang/NAS3R
- Fork on GitHub
- Guo-astro/nas3r
- Upstream stars
- 121
- Category
- Finance, data and research
- Language
- Python
- License
- MIT
- Forked
- 2026-05-03
- Sync status
- In syncLast synced 2026-10-10
More in Finance, data and research
Kronos is a foundation model for financial K-line data. It helps forecast market sequences from OHLCV inputs and is meant for market forecasting and research.
Forked 2026-10-04Last synced 2026-10-10License: MITFinance, data and researchGitHub
An open data platform that gives analysts, quants and AI agents access to financial data such as equities, crypto, options and economics through Python.
Forked 2026-09-26Last synced 2026-10-10Custom license (see repository)Finance, data and researchGitHub
A curated list of libraries, packages and resources for systematic and quantitative trading across crypto, stocks, futures, options and FX. It works as a starting index for building trading systems.
Forked 2026-09-25Last synced 2026-10-10License: MITFinance, data and researchGitHub
A tool that collects new arXiv papers every day and summarizes them with AI, published as a GitHub Pages site. It helps researchers keep up with papers and highlight topics they care about.
Forked 2026-08-17Last synced 2026-10-10Custom license (see repository)Finance, data and researchGitHub