AdaptVPR introduces a route-aware generative augmentation framework that creates hard positive examples for Visual Place Recognition (VPR) training. It uses a vision‑language model to assess scene editability, a rule‑based scheduler to select generation routes, and a VPR‑oriented verification scheme to ensure geometric consistency and appearance diversity. The resulting AdaptCities dataset contains 160K verified synthetic hard positives, leading to consistent performance gains across VPR baselines, including up to 9.2% improvement in R@1 under challenging domain shifts.
arXiv:2609.36616v1 Announce Type: new Abstract: Historical street-view imagery records urban evolution, but uneven coverage leaves substantial gaps in historical records. Generating plausible past ap...
The paper investigates using diffusion-based generative image editing to improve object detector robustness against domain shifts, specifically camouflaged military vehicle detection. By synthetically adding foliage, netting, and multi‑spectral camouflage to training data with models such as Qwen Image Edit 2509 and Flux.2 Dev, the authors demonstrate significant mAP gains (up to +20.1 for foliage) over detectors trained on uncamouflaged data. LoRA fine‑tuning further boosts performance for the more challenging multi‑spectral camouflage.
arXiv:2505.12254v3 Announce Type: replace-cross Abstract: Existing visual place recognition (VPR) datasets predominantly rely on vehicle-mounted imagery, offer limited multimodal diversity, and under...
The paper presents MegaEvent, an event‑based visual place recognition system that remains robust to viewpoint changes. By converting five large‑scale geo‑tagged datasets into synthetic event streams and fine‑tuning a vision transformer with a multi‑loss function, MegaEvent achieves an average Recall@1 of 82% on three event‑based localization datasets, outperforming existing methods by 20 recall points. The authors also introduce the Springfield‑Event‑VPR dataset, a 3.7 km walking route recorded in three camera orientations, where MegaEvent surpasses the strongest baseline by 9 recall points.
The paper introduces Depth‑Aware Distillation (DAD), a method that conditions a pretrained Vision Foundation Model’s token representations on geometry inferred by a Geometric Foundation Model, without using a depth sensor. DAD projects image‑aligned depth into the VFM token space and selectively modulates visual representations through channel‑wise geometric conditioning. On the WildCross benchmark, DAD raises average inter‑sequence Recall@1 from 61.41% to 66.37% and Recall@5 from 65.86% to 72.49%, especially improving performance under reverse traversal and long‑term appearance variation.
arXiv:2610.00994v1 Announce Type: new Abstract: Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it. We introduce V...
arXiv:2606. 31603v1 Announce Type: cross Abstract: Semantic segmentation models struggle with data sparsity and rare or visually diverse regions, e.
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.
arXiv:2607. 22705v1 Announce Type: cross Abstract: Object-centric learning aims to represent scenes as objects whose properties can be reused in new combinations.
Historical street-view imagery records urban evolution, but uneven coverage leaves substantial gaps in historical records. Generating plausible past appearances requires restoring changed structures w...
arXiv:2607. 00491v1 Announce Type: cross Abstract: Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input.
arXiv:2607.20116v2 Announce Type: replace Abstract: Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, diff...