AMAP-ML/FE2E
[CVPR 2026] Beyond Generation: Advancing Image Editing Priors for Depth and Normal Estimation
This project helps computer vision researchers and 3D graphics professionals analyze single images to understand their three-dimensional structure. By taking a single image, it can accurately output detailed depth maps (how far away objects are) and surface normal maps (the orientation of surfaces). This is useful for tasks like scene understanding, 3D reconstruction, and robot perception.
195 stars.
Use this if you need to extract precise depth and surface orientation information from individual photographs without requiring specialized hardware or multiple images.
Not ideal if you need to train your own model from scratch, as the current release focuses on inference and evaluation rather than custom training.
Stars
195
Forks
7
Language
Python
License
MIT
Category
Last pushed
Mar 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/AMAP-ML/FE2E"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bytedance/InfiniteYou
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
River-Zhang/ICEdit
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image...
muzishen/IMAGHarmony
🧩 IMAGHarmony 🧩: Controllable image editing with consistent object quantity and layout. A...
TencentARC/BrushNet
[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting...
ermongroup/SDEdit
PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations