Skip to content

2024.10.30 - #13 - Vision-Language Model (VLM), Large Spatial Model, PLGS, Niantic Scaniverse #15

@changh95

Description

@changh95

Interesting papers

Meta의 'An Introduction to Vision-Language Modeling'

image

VLM Survey paper

image

Large Spatial Model: End-to-end Unposed Images to Semantic 3D

image

Where Am I and What Will I See: AN AUTO-REGRESSIVE MODEL FOR SPATIAL LOCALIZATION AND VIEW PREDICTION

image

PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting

image

RANSAC Back to SOTA: A Two-stage Consensus Filtering for Real-time 3D Registration

image

image

Metadata

Metadata

Labels

No labels
No labels

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions