INSIGHT: Indoor Scene Intelligence from Geometric-Semantic Hierarchy Transfer for Public Safety
cs.CV, cs.ET
Submitted: 2026-04-25
Updated: 2026-10-27
Code: https://github.com/alexdimopoulos/insight-sam3
Terminology
Sources
- Cross-Dataset Semantic Segmentation Performance Analysis: Unifying NIST Point Cloud City Datasets for 3D Deep Learning
- SAM 3: Segment Anything with Concepts
- Joint 2D-3D-Semantic Data for Indoor Scene Understanding
- PP-OCR: A Practical Ultra Lightweight OCR System
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