The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset
cs.CV, cs.LG, cs.RO
Submitted: 2026-06-01
Updated: 2026-11-07
Code: https://github.com/autowarefoundation/autoware
Project page: https://kitscenes.com
Terminology
Sources
- MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
- GlobalMapNet: An Online Framework for Vectorized Global HD Map Construction
- HisTrackMap: Global Vectorized High-Definition Map Construction via History Map Tracking
- Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping
- Generation of Training Data from HD Maps in the Lanelet2 Framework
- Depth Anything 3: Recovering the Visual Space from Any Views
- UniDAC: Universal Metric Depth Estimation for Any Camera
- ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction
- LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset
- Users prefer Jpegli over same-sized libjpeg-turbo or MozJPEG
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