thunderbolt215 / UniPerceptLinks
UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture
☆49Updated this week
Alternatives and similar repositories for UniPercept
Users that are interested in UniPercept are comparing it to the libraries listed below
Sorting:
- MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills [SIGGRAPH 2025]☆71Updated 3 months ago
- [NeurIPS 2025 Spotlight] VisualQuality-R1 is the first open-sourced NR-IQA model can accurately describe and rate the image quality.☆144Updated 2 months ago
- CAR: Controllable AutoRegressive Modeling for Visual Generation☆127Updated last year
- Training-Free Text-Guided Image Editing Using Visual Autoregressive Model☆71Updated 8 months ago
- MC$^2$: Multi-concept Guidance for Customized Multi-concept Generation☆31Updated last year
- Official code for our CVPR 2025 paper: "Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption"☆63Updated 3 months ago
- [SIGGRAPH ASIA'25] BlobCtrl: Taming Controllable Blob for Element-level Image Editing☆25Updated last month
- Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model (SIGGRAPH 2024)☆37Updated last year
- Repo for "Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content"☆38Updated 7 months ago
- ☆34Updated last year
- [CVPR 2025] Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution☆213Updated 3 weeks ago
- AAAI2026 X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learning☆87Updated last month
- Official repository for “DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation”☆153Updated last week
- [CVMJ 2025] Neural Video Fields Editing☆80Updated 6 months ago
- Official Implementation of VideoDPO☆155Updated 7 months ago
- Official repository of the paper InstructBrush: Learning Attention-based Instruction Optimization for Image Editing☆16Updated last year
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025)☆33Updated 5 months ago
- [ECCV2024] Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation☆67Updated 9 months ago
- Implementation code of the paper MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing☆71Updated 5 months ago
- [ICCV 2025] FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing☆70Updated 4 months ago
- ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models☆88Updated 3 months ago
- ☆19Updated last year
- ☆38Updated 9 months ago
- Training Autoregressive Image Generation models via Reinforcement Learning☆48Updated last month
- ☆41Updated last year
- [[NeurIPS 2025] UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions☆78Updated 5 months ago
- (ICCV2025) EEdit⚡: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing☆60Updated 3 months ago
- [ICCV 2025] Official implementation of "Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing"☆28Updated 8 months ago
- Q-Insight is open-sourced at https://github.com/bytedance/Q-Insight. This repository will not receive further updates.☆142Updated 7 months ago
- ④[ECCV 2024 Oral, Comparison among Multiple Images!] A study on open-ended multi-image quality comparison: a dataset, a model and a bench…☆86Updated last year