Views
No views yet
1sudo apt install zstd # 或 brew install zstd
2
3# 下载 (1.8 GB)
4huggingface-cli download taopeng/ace0-ugcr-uar ace0-ugcr-uar.tar.zst --local-dir .
5
6# 解压
7tar --use-compress-program=unzstd -xf ace0-ugcr-uar.tar.zst20260415_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%) |
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)