Branch-and-bound over SE(3) with derived bounds gives globally optimal L2 ICP registration independent of initialization.

技術屬性

欄位內容為文獻擷取紀錄的原文用語(英文),以原文為據;「未查證」表示本研究尚未讀到該資訊,不代表該方法不具備此能力。

Go-ICP 的技術屬性
感測輸入["Kinect (bowl and loom point sets)", "structured light 3D scanner (denture point set)", "RGB-D depth images from public datasets (camera localization dataset [68], RGB-D Object Dataset [69])"]
原文測試平台未記錄
狀態估計nested best-first branch-and-bound: an outer BnB over rotation (angle-axis cube [-pi, pi]^3 split by octree) calls an inner BnB over translation (cube [-xi, xi]^3); per-point residual bounds come from rotation and translation uncertainty radii; whenever a better cube is found, local ICP is run from it and its result tightens the upper bound; the search stops when the best error minus the lower bound is below epsilon; outliers handled with a trimmed L2 error using Introselect (O(N))
資料關聯closest point under the L2 residual; for bound evaluation closest distances come either from a kd-tree or, more often in the experiments, from a precomputed 3-D Euclidean distance transform (300 x 300 x 300 grid, approximate); local ICP always uses a kd-tree
時間表示不適用
去畸變不適用
迴圈閉合none
全域最佳化globally optimal search over SE(3) (abstract)
地圖表示3D point sets
先驗資訊no initial pose needed; requires a bounded translation domain [-xi, xi]^3, point sets pre-normalized to [-1, 1]^3, a convergence threshold epsilon and, for partial overlap, a hand-chosen trimming percentage rho
可輸出幾何rigid transformation
計算需求C++ on a standard PC with an Intel i7 3.4 GHz CPU; with the distance transform, mean and longest times 1.6 s and 22.3 s (bunny) and 1.5 s and 28.9 s (dragon) for 1000 data points against 20,000 to 40,000 model points; kd-tree runs typically 40 to 50 times longer; trimmed partial-overlap runs 0.45 to 18.4 s mean and up to 107.3 s max (Table 1); camera localization 32 s mean and 178 s max

使用設備

原文使用的感測器、運算硬體與載具(equipment)。型號保留原文寫法,連結到設備頁中同一型號的歸併名稱;角色依原文用途分為方法輸入、資料集感測器、執行運算平台、參考或真值量測(reference or ground truth)與比較對象設備。

原文使用的設備
類別型號(原文寫法)角色資料集原文規格出處
RGB-D 相機Kinect資料集感測器bowl and loom point sets collected by the authors原文未報告(Yang et al., 2016, Sec. 6.3)
運算硬體Intel i7 3.4GHz CPU (standard PC)執行運算平台未標示C++ implementation(Yang et al., 2016, Sec. 6)
其他structured light 3D scanner資料集感測器denture point set原文未報告(Yang et al., 2016, Sec. 6.3, footnote 6)

作者報告的優勢與限制

優勢

限制

營建工程相關證據

原文未報告(僅有物件模型、辦公室場景深度影像定位與 RGB-D 外參校正示例,無營建場域)

原文驗證環境:模擬、公開基準

報告的性能數據

以下是原文作者報告的性能數值(author-reported results),不是本研究重新量測的結果。每張圖只並列同一個比較組(comparison group,同一張表、同一組實驗設定)內的方法;不同比較組之間的數值不可直接比較,也不構成排名。

本方法共出現在 9 個比較組,合計 87 筆紀錄。以下列出本方法紀錄最多的 4 組,其餘 5 組列在最後,並連到性能比較頁。

Yang et al., 2016 · Table 1 本方法 40 筆

表格設定(擷取紀錄原文):Go-ICP with distance transform and trimming on 10 partially overlapping point-set pairs; 100 random relative poses per pair and direction; N = 1000 data points; epsilon = 0.001 x K; all tasks registered correctly (Yang et al., 2016, Table 1)

mean/max time (s),Bunny (Stanford 3D) · A to B

這張表在此指標與資料序列只列出本方法一筆,沒有可並列的其他方法,因此不畫圖,數值與出處見下表。這是 Yang et al., 2016 在此表設定下報告的數值(author-reported results),不代表方法在其他資料或設定下的表現。

統計量:平均值(mean);對齊方式:未對齊;單位:s;場景:object scans

數值與出處
方法(原文寫法)報告值出處
Go-ICP (DT, trimming rho = 10%)本方法原文提出硬體:Intel i7 3.4 GHz PC0.81 s(Yang et al., 2016, Table 1)

Zhou et al., 2016 · Table 1 本方法 12 筆

表格設定(擷取紀錄原文):25 synthetic range-image pairs per noise level; RMSE of ground-truth correspondence distances, unit surface diameter; GoICP variants on 1,000 points (Zhou et al., 2016, Table 1)

Average RMSE,Synthetic range images (AIM@SHAPE, Berkeley Angel, Stanford Bunny) · sigma 0

只並列這張表在相同設定下報告的方法;以「本方法:」開頭者為本頁方法。失敗、未執行與未報告以標記呈現,不是 0。

按 Tab 進入圖表後,用上下方向鍵逐一瀏覽各類別,Esc 關閉提示框;也可開啟表格檢視閱讀全部數值。

這些是 Zhou et al., 2016 在此表設定下報告的數值(author-reported results),只能在同一個比較組內對照,不代表方法在其他資料或設定下的表現。

統計量:平均值(mean);對齊方式:未對齊;單位:surface diameter;場景:synthetic

資料來源作者報告值(Zhou et al., 2016, Table 1)

數值與出處
方法(原文寫法)報告值出處
GoICP [42]本方法0.029(Zhou et al., 2016, Table 1)
GoICP-Trimming [42]本方法0.035(Zhou et al., 2016, Table 1)
Super 4PCS [26]0.012(Zhou et al., 2016, Table 1)
OpenCV [8] (implementation of Drost et al.)0.009(Zhou et al., 2016, Table 1)
PCL [19,34] (PCL implementation of Rusu et al.)0.003(Zhou et al., 2016, Table 1)
CZK [7] (Choi et al. variant of Rusu's algorithm)0.003(Zhou et al., 2016, Table 1)
Our approach (FGR)原文提出0.003(Zhou et al., 2016, Table 1)

Zhou et al., 2016 · Table 2 本方法 12 筆

指標running time per pairwise registration (s)

表格設定(擷取紀錄原文):Average running time of each global method on each synthetic model and over all models (the number of tests averaged per model is not stated; each model has five range-image pairs at three noise levels); GoICP variants on 1,000 downsampled points, others at full resolution; single thread (Zhou et al., 2016, Table 2)

running time per pairwise registration (s),Synthetic range images · Bimba (9,416 points avg)

只並列這張表在相同設定下報告的方法;以「本方法:」開頭者為本頁方法。失敗、未執行與未報告以標記呈現,不是 0。

按 Tab 進入圖表後,用上下方向鍵逐一瀏覽各類別,Esc 關閉提示框;也可開啟表格檢視閱讀全部數值。

這些是 Zhou et al., 2016 在此表設定下報告的數值(author-reported results),只能在同一個比較組內對照,不代表方法在其他資料或設定下的表現。

統計量:平均值(mean);對齊方式:未對齊;單位:s;場景:synthetic

資料來源作者報告值(Zhou et al., 2016, Table 2)

數值與出處
方法(原文寫法)報告值出處
GoICP [42]本方法硬體:Intel Core i7-5960X 3.00 GHz, single thread19.3 s(Zhou et al., 2016, Table 2)
GoICP-Trimming [42]本方法硬體:Intel Core i7-5960X 3.00 GHz, single thread19.4 s(Zhou et al., 2016, Table 2)
OpenCV [8] (implementation of Drost et al.)硬體:Intel Core i7-5960X 3.00 GHz, single thread41 s(Zhou et al., 2016, Table 2)
Super 4PCS [26]硬體:Intel Core i7-5960X 3.00 GHz, single thread311.4 s(Zhou et al., 2016, Table 2)
PCL [19,34] (PCL implementation of Rusu et al.)硬體:Intel Core i7-5960X 3.00 GHz, single thread18.2 s(Zhou et al., 2016, Table 2)
CZK [7] (Choi et al. variant of Rusu's algorithm)硬體:Intel Core i7-5960X 3.00 GHz, single thread12.8 s(Zhou et al., 2016, Table 2)
Our approach (FGR)原文提出硬體:Intel Core i7-5960X 3.00 GHz, single thread0.13 s(Zhou et al., 2016, Table 2)

Yang et al., 2016 · Text Sec. 6.2 本方法 7 筆

表格設定(擷取紀錄原文):Same setting as other Text Sec. 6.2 rows; 1,000 data points vs 20,000 to 40,000 model points (Yang et al., 2016, Text Sec. 6.2)

mean/longest running time,Stanford bunny · 1,000 tests

這張表在此指標與資料序列只列出本方法一筆,沒有可並列的其他方法,因此不畫圖,數值與出處見下表。這是 Yang et al., 2016 在此表設定下報告的數值(author-reported results),不代表方法在其他資料或設定下的表現。

統計量:平均值(mean);對齊方式:未對齊;單位:s;場景:object scans

數值與出處
方法(原文寫法)報告值出處
Go-ICP (DT)本方法原文提出硬體:Intel i7 3.4 GHz PC1.6 s(Yang et al., 2016, Sec. 6.2)

其他比較組

列出其餘 5 個比較組

來源

  • Yang et al., 2016

    Jiaolong Yang, Hongdong Li, Dylan Campbell, Yunde Jia(2016)Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set RegistrationIEEE Transactions on Pattern Analysis and Machine Intelligence, 38(11):2241-2254

    同儕審查已出版已讀全文經典查證後修正

回到方法圖鑑

選擇開啟Esc關閉