GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping

2026-08-28 · Xiang Yang, Yongli Wang, Yunsheng Zhang arxiv

Existing feed-forward 3D reconstruction methods typically process a bounded number of images and recover cameras and geometry in local or internally normalized frames. Extending them to large-scale UAV mapping requires scalable multi-chunk processing and reliable aggregation, while full Sim(3) alignment can become unstable for near collinear trajectories. We present GeoFF3D, which combines a coordinate-anchored model with a spatial large-scale reconstruction framework (SLRF). The model uses georeferenced camera translations and optional geometric priors to predict camera poses and dense point maps directly in a gravity-aligned Z-up metric frame. SLRF partitions images into spatially overlapping chunks, propagates shared-view priors, and aggregates local reconstructions hierarchically, while remaining applicable to different bounded-view models. Across nine aerial mapping blocks, GeoFF3D achieves the best average reconstruction quality, improving F@5 from 0.829 for Pi3X + SLRF to 0.877. On long UAVScenes sequences, it reaches 0.848, compared with 0.687 for Pi3X + SLRF and 0.451 for the strongest evaluated SLAM/streaming baseline. GeoFF3D reconstructs 2,000 images in approximately five minutes, demonstrating scalable and robust large-scale UAV reconstruction.The code is available at https://github.com/yanxian-ll/GeoFF3D.

📄 PDF Abstract BibTeX arXiv:2608.28288

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction

CoANeRV: Coordinate-Aware Token-Space Neural Video Representation

2026-08-14 · Jialong Guo, Ke Liu, Mengxuan Li, Jiajun Bu 외 arxiv

Neural representations for videos (NeRV) have shown strong reconstruction fidelity by storing video-specific information in network weights. However, existing formulations typically require either costly per-video optimi…

APO: Alpha-Divergence Preference Optimization

2025-12-28 · Wang Zixian arxiv

Two divergence regimes dominate modern alignment practice. Supervised fine-tuning and many distillation-style objectives implicitly minimize the forward KL divergence KL(q || pi_theta), yielding stable mode-covering upda…

Reinforcement Learning

FAST3DIS: Feed-forward Anchored Scene Transformer for 3D Instance Segmentation

2026-03-27 · Changyang Li, Xueqing Huang, Shin-Fang Chng, Huangying Zhan 외 arxiv

While recent feed-forward 3D reconstruction models provide a strong geometric foundation for scene understanding, extending them to 3D instance segmentation typically relies on a disjointed "lift-and-cluster" paradigm. G…

3D Instance Segmentation Representation Learning Contrastive Learning Scene Understanding

TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

2026-05-12 · Jisu Nam, Jahyeok Koo, Soowon Son, Jaewoo Jung 외 arxiv

Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging a…

Scene Understanding 3D Reconstruction

Prototypical Variational Autoencoders

2021-09-29 · Dario Augusto Borges Oliveira, Laura Elena Cue La Rosa

Variational autoencoders are unsupervised generative models that implement latent space regularization towards a known distribution, enabling stochastic synthesis from straightforward sampling procedures. Many works prop…