ElasticDino: Dense Semantic Features Using Elastic Deformations
cs.CV, cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Project page: https://odusseys.github.io/ElasticDino
Terminology
Sources
- LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models
- DINOv2: Learning Robust Visual Features without Supervision
- UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders
- AnyUp: Universal Feature Upsampling
- Quantifying the Carbon Emissions of Machine Learning
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