CPU-only house-scale TSDF reconstruction on Google Tango devices: spatially hashed 16^3-voxel chunks allocated by frustum culling and garbage-collected, dynamic truncation and space carving from a trained depth-noise model, visual-inertial odometry corrected by scan-to-TSDF ICP, and lazy per-chunk incremental meshing; no loop closure.

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。

CHISEL 的技術屬性
感測輸入Google Tango 'Peanut' phone: projective depth sensor (6 Hz), 120 deg wide-angle tracking camera (60 Hz), 4 MP colour camera (30 Hz), six-axis gyroscope and accelerometer、Google Tango 'Yellowstone' tablet: projective depth sensor (3 Hz), same tracking camera, 4 MP colour camera (30 Hz)、Kinect RGB-D data of the Freiburg (TUM) benchmark for memory experiments
原文測試平台handheld (Tango phone and tablet; office building floor, 175 m corridor, apartment, outdoor night scene)
狀態估計Onboard visual-inertial odometry (EKF fusing wide-angle camera and inertial data with 2D feature tracking at 60 Hz; the paper refers to Kottas et al. and the MSCKF for details) with sparse keypoint mapping used as a black box, incrementally corrected by scan-to-model ICP against the TSDF (residual = TSDF value at each transformed point, gradient by central differences); corrective transforms accumulated per scan
資料關聯Implicit point-to-TSDF association via the signed distance value and its gradient (first-order projection onto the zero level set)
時間表示discrete poses
去畸變不適用 (depth camera)
迴圈閉合none online; Fig. 7 shows a corridor corrected only after offline bundle adjustment
全域最佳化none online (offline bundle adjustment used only for the Fig. 7 corridor illustration)
地圖表示dynamic spatially hashed TSDF: chunks of 16 x 16 x 16 voxels in a hash map, allocated on frustum intersection and garbage-collected when not updated; each voxel stores a 16-bit fixed-point SDF and 16-bit weight plus 8-bit RGB and colour weight; dynamic truncation from a trained depth-noise model; space carving
先驗資訊none
可輸出幾何per-chunk triangle meshes from incremental marching cubes (lazy, asynchronous), coloured by trilinear interpolation; map savable to disk; 2 to 3 cm voxels on the devices
計算需求CPU only on the mobile device (no general-purpose GPU computing); single-scan fusion 62 to 200 ms on the Tango tablet and 14 to 58 ms on a desktop depending on the fusion mode (Fig. 9e)

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
行動掃描設備Google Tango 'Yellowstone' tablet方法輸入未標示4 GB RAM, quad-core CPU, Nvidia Tegra K1 graphics, 120 deg FOV tracking camera at 60 Hz, projective depth sensor at 3 Hz, 4 megapixel colour sensor at 30 Hz(Klingensmith et al., 2015, Sec. IV-A)
行動掃描設備Google Tango 'Peanut' mobile phone方法輸入未標示2 GB RAM, quad-core CPU, six-axis gyroscope and accelerometer, 120 deg wide-angle tracking camera at 60 Hz, projective depth sensor at 6 Hz, 4 megapixel colour sensor at 30 Hz(Klingensmith et al., 2015, Sec. IV-A)
RGB-D 相機Kinect資料集感測器Freiburg (TUM) RGB-D benchmarksensor loops around a central desk in a roughly 12 by 12 m room; the paper writes only 'Kinect', manufacturer inferred from the product name(Klingensmith et al., 2015, Sec. IV-D)
運算硬體desktop machine (model not reported)執行運算平台未標示used only for the fusion-time comparison in Fig. 9e(Klingensmith et al., 2015, Sec. IV-C; Fig. 9e)
其他motion capture system (model not reported)參考或真值量測Freiburg (TUM) RGB-D benchmarkground-truth poses of the Freiburg dataset(Klingensmith et al., 2015, Sec. IV-D)

作者報告的優勢與限制

優勢

限制

營建工程相關證據

論文未在施工現場測試。實例包括整層辦公大樓、約 175 公尺走廊、公寓與夜間戶外場景,皆以手持 Tango 裝置即時掃描(Fig. 1、7、8)。在行動裝置上即時建立 2 至 3 公分解析度的樓層模型,符合低成本手持室內掃描的需求;但系統會累積漂移(走廊末端約 5 公尺),且論文沒有以幾何真值評估精度,用於量測用途前需另以控制點校核(推論)。

原文驗證環境:公開基準、已完工建築

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 6 個比較組,合計 50 筆紀錄。以下列出本方法紀錄最多的 4 組,其餘 2 組列在最後,並連到性能比較頁。

Klingensmith et al., 2015 · Fig. 9e 本方法 32 筆

資料集與序列authors' Room (apartment) dataset · Room

表格設定(擷取紀錄原文):Time to fuse a single depth scan on the 'Room' (apartment, Fig. 1b) dataset for each fusion mode; mean and standard deviation printed as 'mean +- std' (Klingensmith et al., 2015, Fig. 9e)

single scan fusion time (ms.),authors' Room (apartment) dataset · Room

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 Klingensmith 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 apartment, handheld Tango

資料來源作者報告值(Klingensmith et al., 2015, Fig. 9e)

數值與出處
方法(原文寫法)報告值出處
CHISEL: Raycast, no colour, no carving(desktop (model not reported))本方法原文提出14 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Raycast, no colour, no carving(Google Tango 'Yellowstone' tablet)本方法原文提出62 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Raycast, colour, no carving(desktop (model not reported))本方法原文提出20 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Raycast, colour, no carving(Google Tango 'Yellowstone' tablet)本方法原文提出80 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Raycast, no colour, carving(desktop (model not reported))本方法原文提出53 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Raycast, no colour, carving(Google Tango 'Yellowstone' tablet)本方法原文提出184 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Raycast, colour, carving(desktop (model not reported))本方法原文提出58 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Raycast, colour, carving(Google Tango 'Yellowstone' tablet)本方法原文提出200 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Projection mapping, no colour, no carving(desktop (model not reported))本方法原文提出33 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Projection mapping, no colour, no carving(Google Tango 'Yellowstone' tablet)本方法原文提出106 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Projection mapping, colour, no carving(desktop (model not reported))本方法原文提出39 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Projection mapping, colour, no carving(Google Tango 'Yellowstone' tablet)本方法原文提出125 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Projection mapping, no colour, carving(desktop (model not reported))本方法原文提出34 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Projection mapping, no colour, carving(Google Tango 'Yellowstone' tablet)本方法原文提出116 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Projection mapping, colour, carving(desktop (model not reported))本方法原文提出40 ms(Klingensmith et al., 2015, Fig. 9e)
CHISEL: Projection mapping, colour, carving(Google Tango 'Yellowstone' tablet)本方法原文提出128 ms(Klingensmith et al., 2015, Fig. 9e)

Han & Fang, 2018 · Table IV 本方法 6 筆

表格設定(擷取紀錄原文):Efficiency comparison between CPU-based CHISEL and FlashFusion on TUM fr3/office at three voxel resolutions; time per operation in ms (Han & Fang, 2018, Table IV)

TSDF Fusion (ms),TUM RGB-D · fr3/office (5mm voxels)

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 Han & Fang, 2018 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:原文未報告;單位:ms;場景:indoor office desk loop

資料來源作者報告值(Han & Fang, 2018, Table IV)

數值與出處
方法(原文寫法)報告值出處
CHISEL本方法硬體:Intel Core i7 7700 @3.6 GHz (CPU only)483 ms(Han & Fang, 2018, Table IV)
FlashFusion原文提出硬體:Intel Core i7 7700 @3.6 GHz (CPU only)3.6 ms(Han & Fang, 2018, Table IV)

Klingensmith et al., 2015 · Table I 本方法 4 筆

資料集與序列Freiburg (TUM) RGB-D benchmark · Freiburg 5m (desk loop)

表格設定(擷取紀錄原文):Voxel statistics for the Freiburg 5 m depth-frustum reconstruction; share of the bounding box per voxel class (culled voxels are not stored) (Klingensmith et al., 2015, Table I)

% of Bounding Box (Unknown Culled),Freiburg (TUM) RGB-D benchmark · Freiburg 5m (desk loop)

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 Klingensmith et al., 2015 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:%;場景:indoor room about 12 by 12 m, Kinect loop around a central desk (Freiburg dataset; carrying mode not stated)

數值與出處
方法(原文寫法)報告值出處
CHISEL spatially hashed TSDF本方法原文提出77%(Klingensmith et al., 2015, Table I)

Klingensmith et al., 2015 · Table II 本方法 4 筆

資料集與序列authors' Room (apartment) dataset · Room

表格設定(擷取紀錄原文):Per-frame mesh generation and TSDF update (colorization, space carving, projection mapping) on the 'Room' dataset; platform not stated (update time equals the tablet value in Fig. 9e) (Klingensmith et al., 2015, Table II)

Meshing Time (ms.),authors' Room (apartment) dataset · Room

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 Klingensmith 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 apartment, handheld Tango

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

數值與出處
方法(原文寫法)報告值出處
256^3 Fixed Grid (baseline)硬體:not stated2067 ms(Klingensmith et al., 2015, Table II)
16^3 Spatial Hashing (CHISEL)本方法原文提出硬體:not stated102 ms(Klingensmith et al., 2015, Table II)

其他比較組

列出其餘 2 個比較組

來源

  • Klingensmith et al., 2015

    Matthew Klingensmith, Ivan Dryanovski, Siddhartha S. Srinivasa, Jizhong Xiao(2015)Chisel: Real Time Large Scale 3D Reconstruction Onboard a Mobile Device using Spatially Hashed Signed Distance FieldsRobotics: Science and Systems XI (RSS 2015), 原文未報告 (paper 40)

    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