3L-D: A Low-Light Level Dataset from a Sensor-Agnostic, Alignment-Preserving Acquisition Framework
cs.CV, cs.DB
Submitted: 2026-11-02
Updated: 2026-11-02
Project page: https://3l-d.github.io/3L-Dataset
Terminology
Sources
- Deep Retinex Decomposition for Low-Light Enhancement
- The Intrinsic Dimension of Images and Its Impact on Learning
- Estimating Dataset Dimension via Singular Metrics under the Manifold Hypothesis: Application to Inverse Problems
- Verifying the Union of Manifolds Hypothesis for Image Data
- Robust estimation of the intrinsic dimension of data sets with quantum cognition machine learning
- BVI-Lowlight: Fully Registered Benchmark Dataset for Low-Light Video Enhancement
- DarkVision: A Benchmark for Low-light Image/Video Perception
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs