TransNormal-2

TransNormal-2

longxiang-ai

Official implementation of "TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation". Single-step surface normal estimation for general scenes and transparent objects. Code and model weights will be released progressively.

12 Stars
0 Forks
0 Watchers
Python Language
other License
69.6 SrcLog Score
Cost to Build
$1.65M
Market Value
$2.00M

Growth over time

1 data points  ·  2026-09-20 → 2026-09-20
Stars Forks Watchers
💬

How do you feel about this project?

Ask AI about TransNormal-2

Question copied to clipboard

What is the longxiang-ai/TransNormal-2 GitHub project? Description: "Official implementation of "TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation". Single-step surface normal estimation for general scenes and transparent objects. Code and model weights will be released progressively.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone TransNormal-2

Clone via HTTPS

git clone https://github.com/longxiang-ai/TransNormal-2.git

Clone via SSH

[email protected]:longxiang-ai/TransNormal-2.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the TransNormal-2 issue tracker:

Open GitHub Issues