PGGT-Loc: Primitive-Grounded Geometry Transformer for Feed-Forward Camera Localization
cs.CV, cs.RO
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: Accepted at NeurIPS 2026. 24 pages, 14 figures, including appendices. Code and models: https://github.com/3dv-casia/PGGT-Loc
Code: https://github.com/3dv-casia/PGGT-Loc
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training
- Robust Image Retrieval-based Visual Localization using Kapture
- Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
- DisCo-FLoc: Semantic-Free Floorplan Localization via $SE(2)$-Aware Contrastive Disambiguation
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