KinectFusion fuses depth frames into a global TSDF volume on the GPU and tracks each frame by coarse-to-fine point-to-plane ICP against a raycast prediction of the fused model.

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。

KinectFusion 的技術屬性
感測輸入RGB-D
原文測試平台hand-held Kinect (Fig. 1; Sec. 1; experiment 5 with 560 x 4 free-moving frames)、Kinect fixed in place observing a tabletop scene on a turntable rotated through a full turn in about 19 s (560 frames)
狀態估計coarse-to-fine point-to-plane ICP against the raycast model prediction over the bottom 3 pyramid levels with at most 4, 5 and 10 iterations (coarse to fine); small-angle linearisation gives per-correspondence 6x6 systems summed on the GPU by tree reduction and solved by Cholesky on the CPU; a null-space check and an increment-magnitude check switch the system into relocalisation mode
資料關聯projective data association on bilateral-filtered depth (vertex and normal map pyramid, L = 3), rejecting pairs by vertex distance and normal-angle thresholds; raw depth, not the filtered depth, is fused into the TSDF
時間表示discrete poses (every frame)
去畸變原文未報告
迴圈閉合none explicit; loops are closed only implicitly by frame-to-model tracking (turntable loop-closing frames nearly overlap after one pass and more tightly after four passes); on tracking failure an interactive relocalisation asks the user to align the live depth frame with the prediction from the last known pose
全域最佳化none
地圖表示single fixed-extent dense TSDF volume in GPU memory storing truncated distance and weight (16 bits per component); projective TSDF with nearest-neighbour depth lookup and weighted running average, optional weight cap for moving-average reconstruction of dynamic scenes; 256^3 voxels in the turntable experiments, 64^3 to 512^3 evaluated
先驗資訊none
可輸出幾何dense TSDF surface rendered by raycasting; mesh export not reported in sections read
計算需求commodity GPU (model not reported); TSDF update above 65 gigavoxels per second (about 2 ms per full 512^3 volume); tracking at the 30 Hz Kinect frame rate; constant-time tracking and mapping for a given voxel resolution; 64^3 volume with every 6th frame shows graceful degradation

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方法輸入未標示structured-light depth sensor; on-board ASIC produces an 11-bit 640x480 depth map at 30 Hz; conservative range about 0.4 to 8 m used for raycasting; only depth used(Newcombe et al., 2011b, Sec. 2.1; Sec. 3.4)
運算硬體commodity GPU (model not reported)執行運算平台未標示all tracking and mapping on GPU; TSDF update above 65 gigavoxels per second(Newcombe et al., 2011b, Abstract; Sec. 3.3)
其他turntable參考或真值量測未標示tabletop scene rotated through a full rotation in about 19 s (560 frames) with the Kinect fixed, equivalent to a precise circular sensor path(Newcombe et al., 2011b, Sec. 4.1)

作者報告的優勢與限制

優勢

限制

營建工程相關證據

論文未於營建現場測試。作者指出大面積平面會造成 ICP 三自由度不受約束,並將整棟建築重建列為尚未解決的記憶體與漂移問題;這兩點直接對應室內牆面、樓板與大空間掃描情境(推論連結)。另外 Kinect 深度在不反射紅外光的材料、細長結構與掠射角表面會產生空洞(Sec. 2.1),工地的鋼筋、玻璃與斜視牆面可能受影響(推論);論文的迴圈實驗為轉盤定性展示,未提供數值精度。

原文驗證環境:受控實驗

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 5 個比較組,合計 17 筆紀錄。以下列出本方法紀錄最多的 4 組,其餘 1 組列在最後,並連到性能比較頁。

Kerl et al., 2013 · Table III 本方法 10 筆

指標RMSE of absolute trajectory error

表格設定(擷取紀錄原文):RMSE of absolute trajectory error (m) on TUM RGB-D sequences versus RGB-D SLAM (Engelhard, Endres et al.), MRSMap and the PCL KinectFusion implementation (KinFu); dashes = not available (Kerl et al., 2013, Table III)

RMSE of absolute trajectory error,TUM RGB-D · fr1/xyz

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 Kerl et al., 2013 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:均方根誤差(RMSE);對齊方式:原文未報告;單位:m;場景:indoor TUM RGB-D benchmark sequences (carrying mode and scene type not described in the paper)

資料來源作者報告值(Kerl et al., 2013, Table III)

數值與出處
方法(原文寫法)報告值出處
Ours (DVO-SLAM)原文提出0.011 m(Kerl et al., 2013, Table III)
RGB-D SLAM [2], [31]0.014 m(Kerl et al., 2013, Table III)
MRSMap [11]0.013 m(Kerl et al., 2013, Table III)
KinFu (PCL KinectFusion) [5]本方法0.026 m(Kerl et al., 2013, Table III)

Kähler et al., 2015 · Table 1 本方法 4 筆

指標average computation time per frame

表格設定(擷取紀錄原文):Average computation time per frame over the teddy sequence (Kinect for XBOX 360, 640x480 colour and disparity, no IMU) for three visualisation strategies of InfiniTAM and for the KinectFusion [14] and voxel hashing [16] implementations (Kähler et al., 2015, Table 1)

average computation time per frame,authors' teddy sequence · teddy

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 Kähler et al., 2015 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:原文未報告;單位:ms;場景:indoor desk scene

資料來源作者報告值(Kähler et al., 2015, Table 1)

數值與出處
方法(原文寫法)報告值出處
KinectFusion implementation [14](Nvidia Titan X)本方法26.15 ms(Kähler et al., 2015, Table 1(a))
KinectFusion implementation [14](Intel Core i7-5960X)本方法502.69 ms(Kähler et al., 2015, Table 1(a))
Voxel hashing implementation [16]硬體:Nvidia Titan X25.87 ms(Kähler et al., 2015, Table 1(a))

Ghadimzadeh Alamdari et al., 2025 · Table 2 本方法 1 筆

指標Result (run outcome)

資料集與序列Luleå SubT tunnel dataset (Koval et al. 2022)

表格設定(擷取紀錄原文):Run outcome ('Result' column) of each reviewed vision-based method on the Luleå tunnel test dataset; '+' marks methods not integrated with ROS; the '*' (incompatible with VLP-16) symbol is printed on almost every row (Ghadimzadeh Alamdari et al., 2025, Table 2)

Result (run outcome),Luleå SubT tunnel dataset (Koval et al. 2022)

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。

  • 失敗
  • 未執行
  • 未報告(沒有數值,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 Ghadimzadeh Alamdari et al., 2025 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:原文未報告;對齊方式:未對齊;單位:無單位;場景:underground tunnel

資料來源作者報告值(Ghadimzadeh Alamdari et al., 2025, Table 2)

數值與出處
方法(原文寫法)報告值出處
Mono-SLAM無數值失敗註記(擷取紀錄):failed (feature detection and tracking)(Ghadimzadeh Alamdari et al., 2025, Table 2)
PTAM無數值失敗註記(擷取紀錄):failed (initialization for ground floor)(Ghadimzadeh Alamdari et al., 2025, Table 2)
S-PTAM無數值未執行註記(擷取紀錄):未執行 (authors could not run the code)(Ghadimzadeh Alamdari et al., 2025, Table 2)
OV2SLAM無數值未執行註記(擷取紀錄):未執行 (authors could not run the code)(Ghadimzadeh Alamdari et al., 2025, Table 2)
ORB-SLAM (footnote 1)無數值未報告註記(擷取紀錄):success (footnote 1: authors could not run ORB-SLAM 3, so the original ORB-SLAM was used)(Ghadimzadeh Alamdari et al., 2025, Table 2)
DTAM無數值未執行註記(擷取紀錄):未執行 (no publicly available repository)(Ghadimzadeh Alamdari et al., 2025, Table 2)
LSD-SLAM無數值失敗註記(擷取紀錄):failed (feature tracking)(Ghadimzadeh Alamdari et al., 2025, Table 2)
SVO無數值失敗註記(擷取紀錄):failed (tracking)(Ghadimzadeh Alamdari et al., 2025, Table 2)
DSO無數值未執行註記(擷取紀錄):未執行 (authors could not run the code)(Ghadimzadeh Alamdari et al., 2025, Table 2)
Kinetic Fusion本方法無數值未執行註記(擷取紀錄):未執行 (no publicly available repository)(Ghadimzadeh Alamdari et al., 2025, Table 2)
Dense visual SLAM無數值失敗註記(擷取紀錄):failed (feature detection and tracking)(Ghadimzadeh Alamdari et al., 2025, Table 2)
Elastic Fusion SLAM無數值未執行註記(擷取紀錄):未執行 (inconsistent repository)(Ghadimzadeh Alamdari et al., 2025, Table 2)
Realtime onboard VI estimation無數值未執行註記(擷取紀錄):未執行 (no publicly available repository)(Ghadimzadeh Alamdari et al., 2025, Table 2)
Multi-sensor fusion無數值未執行註記(擷取紀錄):未執行 (no publicly available repository)(Ghadimzadeh Alamdari et al., 2025, Table 2)
SOFT-SLAM無數值未執行註記(擷取紀錄):未執行 (no publicly available repository)(Ghadimzadeh Alamdari et al., 2025, Table 2)
MSCKF無數值失敗註記(擷取紀錄):failed (tracking)(Ghadimzadeh Alamdari et al., 2025, Table 2)
ROVIO無數值未執行註記(擷取紀錄):未執行 (authors could not run the code)(Ghadimzadeh Alamdari et al., 2025, Table 2)
OKVIS無數值失敗註記(擷取紀錄):failed (tracking)(Ghadimzadeh Alamdari et al., 2025, Table 2)
VIORB無數值未執行註記(擷取紀錄):未執行 (inconsistent repository)(Ghadimzadeh Alamdari et al., 2025, Table 2)
S-MSCKF無數值未執行註記(擷取紀錄):未執行 (no publicly available repository)(Ghadimzadeh Alamdari et al., 2025, Table 2)
VINS-Mono無數值未報告註記(擷取紀錄):success(Ghadimzadeh Alamdari et al., 2025, Table 2)
STCM-SLAM無數值未執行註記(擷取紀錄):未執行 (no publicly available repository)(Ghadimzadeh Alamdari et al., 2025, Table 2)
Kimera無數值失敗註記(擷取紀錄):failed (feature detection and tracking)(Ghadimzadeh Alamdari et al., 2025, Table 2)
Yolo-SLAM無數值未報告註記(擷取紀錄):other: Result cell reads 'SLAM for dynamic environments'; no run outcome stated(Ghadimzadeh Alamdari et al., 2025, Table 2)

Newcombe et al., 2011b · Text Sec. 1 本方法 1 筆

指標tracking frame rate

資料集與序列live Kinect input

表格設定(擷取紀錄原文):Tracking rate stated in text; tracking and mapping run at the Kinect frame rate in constant time for a given voxel resolution (Newcombe et al., 2011b, Text Sec. 1)

tracking frame rate,live Kinect input

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 Newcombe et al., 2011b 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:原文未報告;對齊方式:未對齊;單位:Hz;場景:indoor room-sized scenes

數值與出處
方法(原文寫法)報告值出處
KinectFusion本方法原文提出硬體:commodity GPU (model not reported)30 Hz(Newcombe et al., 2011b, Sec. 1; Sec. 4.2)

其他比較組

列出其餘 1 個比較組

來源

  • Newcombe et al., 2011b

    Richard A. Newcombe, Shahram Izadi, Otmar Hilliges, David Molyneaux, David Kim, Andrew J. Davison, Pushmeet Kohli, et al.(2011)KinectFusion: Real-time dense surface mapping and tracking2011 10th IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 127-136

    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