Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer
Paper • 2404.14351 • Published • 6
基于 ACE0 (ECCV 2024 Oral) 的两项扩展,提升场景坐标回归的可靠性与光照鲁棒性。
sudo apt install zstd # 或 brew install zstd
# 下载 (1.8 GB)
huggingface-cli download taopeng/ace0-ugcr-uar ace0-ugcr-uar.tar.zst --local-dir .
# 解压
tar --use-compress-program=unzstd -xf ace0-ugcr-uar.tar.zst
解压得到 20260415_s3_upload/ 目录 (~6.4 GB)。
log1p(error) Gaussian NLL + 分阶段训练 85% warmup)| Metric | Baseline | UGCR v5 | UAR Head |
|---|---|---|---|
| 7-Scenes Acc @5cm/5° avg | 88.9% | 89.6% | 90.3% |
| 7-Scenes Acc @2cm/2° heads | 89.3% | 96.1% | 100.0% |
| Indoor6 high-conf pose 数 (mean) | 146.5 | 224.3 (+53%) | 209.7 (+43%) |
详见 experiments/results/final_results.md、paper_ready_report.md、FINAL_RESULTS_EXTENDED.md。
idea2_ugcr/ — UGCR + UAR Head 源码(含 log1p + σ.detach + UAR refine_net)idea1_igda/ — IGDA 系列源码baseline_ace0/ — ACE0 baseline (改动版本)experiments/scripts/ — 训练/评估/出图脚本(含 run_ugcr_v5_full.sh, eval_multi_threshold.py, make_figures.py)experiments/results/ — 全部方法的 pose 结果 + 评估输出 + figures_v2 (2cm/2° boxplot + recall curves)完整 baseline 数据(含 7-Scenes/Aachen/Indoor6 raw 数据集): taopeng/ace0-rgbt-vl