sczhou/CodeFormer
CodeFormer
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Builder
sczhou
sczhou • individual
Stars
17,862
Using upstream star count
Forks
3,710
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Jun 21, 2022
Project creation date
README Summary
CodeFormer is a robust blind face restoration method that uses a Codebook Lookup Transformer to restore degraded face images without prior knowledge of the degradation type. The approach leverages discrete codebook representations and transformer architecture to achieve high-quality face restoration results. This NeurIPS 2022 paper presents a novel solution for handling various face degradation scenarios in a unified framework.
AI Dev Skills
Unmapped
Tags
Taxonomy
AI Trends
Deployment Context
Modalities
Skill Areas
Recent Activity
Updated 4 months ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- high
- Maturity
- research
Categories
PM Skills
Languages
Timeline
- Project created
- Jun 21, 2022
- Forked
- Mar 22, 2026
- Your last push
- 4 months ago
- Upstream last push
- 4 months ago
- Tracked since
- Nov 18, 2025
Similar Repos
pgvector cosine similarity · $0
Loading…