Official Amap technology account showcasing all of Amap's technical innovations.
This paper presents the design, implementation, and experimental evaluation of OceanBase's unitization architecture for large‑scale online map services, demonstrating superior disaster‑recovery, high‑throughput OLTP/OLAP performance, and storage efficiency compared with competing distributed databases.
This article explains how Gaode Map leverages lightweight edge TTS models, dual‑autoregressive large‑model data augmentation, and a configurable audio‑processing DAG to enable users to create highly realistic personalized voice packs from just three recorded sentences.
The article introduces Group Policy Gradient (GPG), a reinforcement‑learning framework that eliminates surrogate loss functions and critic models, directly optimizes the original objective, reduces bias and variance, and achieves state‑of‑the‑art performance on both single‑modal and multimodal tasks.
The paper introduces G3PT, a groundbreaking autoregressive 3D generation model that employs a Cross‑Scale Querying Transformer and multi‑scale tokenization to produce high‑quality meshes from a single image, outperforming diffusion‑based methods and revealing a scaling law for 3D generation.
FantasyTalking generates high-fidelity, coherent talking portraits from a single static image by employing a two-stage audio-visual alignment—global segment-level motion and frame-level lip refinement—combined with face-centric cross-attention for identity preservation and a motion-intensity module that lets users control expression and body movement, achieving superior realism, synchronization, and performance over prior methods.
At ICASSP 2025, Gaode’s two accepted papers present Lenna, a language‑enhanced reasoning detection assistant that adds a DET token to multimodal LLMs and achieves state‑of‑the‑art accuracy on RefCOCO benchmarks, and a chain‑of‑thought image‑editing framework that converts complex prompts into segmented masks and repair prompts for diffusion‑based inpainting, surpassing existing methods.
HumanRig introduces a large‑scale dataset of 11,434 AI‑generated T‑pose humanoid meshes with unified skeletons, skinning weights, joint data and images, and leverages it in a novel automatic rigging pipeline—featuring a prior‑guided skeleton estimator, a U‑shaped point transformer, and a mesh‑skeleton mutual attention network—that significantly outperforms previous methods in skeleton accuracy and skinning quality.
Gaode’s Uninhabited Area project introduces Satellite Rescue, which transmits encrypted, natural‑language emergency messages via satellite and a rescue chatroom to boost response speed, and Offline Navigation, employing quadtree indexing, predictive caching and seamless mode switching to guide users through network‑dead zones, proven in harsh Inner Mongolian terrains.
Gaode Map’s new integrated container architecture, combined with on‑demand loading, package slimming, and multi‑system/device/language support, delivers ultra‑stable, high‑availability navigation with second‑level startup, halved binary size and traffic, enabling efficient, cross‑platform mobile mapping for diverse hardware.
Gaode Map and Xi'an Jiaotong University introduce the “Driving by the Rules” task, releasing the MapDR benchmark that integrates lane‑level traffic‑sign regulations into online‑constructed HD maps, and provide modular (VLE‑MEE) and end‑to‑end (RuleVLM) baselines to evaluate rule extraction and lane association.
