arXiv Computer Vision
MVDG: Efficient Multi-view 3D Disambiguation on Unconstrained Real-World Images
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 1
XDG: Accelerated Visual Disambiguation
arXiv:2608.29733v1 Announce Type: new Abstract: Visual aliasing, also known as the doppelganger problem, remains a key challenge for structure-from-motion (SfM): visually similar but physically disti...
arXiv Computation and Language
4d ago
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
arXiv:2609.38177v1 Announce Type: cross Abstract: Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs...
arXiv Computer Vision
Aug 25
GeoLink: A 3D-aware Framework to Improve Generalization for Cross-view Geo-localization
arXiv:2604.13183v4 Announce Type: replace Abstract: Generalizable cross-view geo-localization aims to match the same location across views in unseen regions and conditions without GPS supervision. It...
arXiv Computer Vision
Aug 24
Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding
arXiv:2608.21136v1 Announce Type: new Abstract: Recently, open-vocabulary zero-shot 3D scene understanding using vision foundation models has emerged as a promising alternative to data-intensive supe...
arXiv AI
Jul 13
MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs
arXiv:2607. 08970v1 Announce Type: cross Abstract: Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model.
arXiv Machine Learning
Jun 24
Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints
arXiv:2606. 24353v1 Announce Type: cross Abstract: Bird's-eye view (BEV) perception fuses multi-camera images into a unified top-down representation for autonomous driving.