Uses voxel-level GPR on sparse LiDAR points to initialize covariance-aware 3D Gaussians for real-time outdoor photorealistic mapping on top of LIVO poses.

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。

GS-LIVM 的技術屬性
感測輸入3D LiDAR、IMU、monocular camera
原文測試平台handheld、wheeled robot
狀態估計ESIKF LiDAR-inertial-visual odometry (tracking thread, output at IMU rate) adopted from SR-LIVO [48] with two changes: original sensor timestamps replace the time-sweep refinement (fixing crashes with spinning LiDAR) and large matrix products are CUDA-accelerated
資料關聯colour point cloud from LIVO; photometric, SSIM, structure-similarity and delta-depth losses for Gaussian optimization
時間表示discrete poses
去畸變不適用
迴圈閉合none; the authors state the tracking method lacks a loop closure detection module and is less accurate than LVI-SAM on some Botanic Garden sequences
全域最佳化none reported
地圖表示voxel-hashed dense map of 3D Gaussians (position, covariance, opacity, zero-degree SH colour) initialized per voxel subgrid from Voxel-GPR predictions: position as the inverse-variance weighted mean, scale from the diagonal of the weighted covariance, rotation set to the identity quaternion
先驗資訊none
可輸出幾何dense 3D Gaussian map and rendered images; no geometric accuracy metric of the map is reported (evaluation covers PSNR, SSIM, LPIPS, runtime, memory and trajectory RPE and ATE only)
計算需求CUDA/C++ with LibTorch under ROS; desktop PC with a 5.50 GHz Intel Core i9-13900HX CPU, 64 GB RAM and an NVIDIA RTX 4060 Laptop 8 GB GPU; Voxel-GPR under 30 ms per batch; all sequences fully mapped on the 8 GB GPU with ns = 3; mapping time equals or nearly equals the sequence duration (e.g., 612 s for a 611 s sequence)

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
LiDARLivox Avia資料集感測器R3LIVE dataset; FAST-LIVO dataset10 Hz; handheld device with built-in IMU and a 15 Hz RGB camera (640 x 512)(Xie et al., 2025, Sec. 4.1)
LiDAROuster-16資料集感測器NTU-VIRALmulti-line spinning LiDAR, sparser than Livox; images 752 x 480(Xie et al., 2025, Sec. 4.1)
LiDARVelodyne VLP-16資料集感測器Botanic Gardenmulti-line spinning LiDAR; images 480 x 300; used for the tracking evaluation(Xie et al., 2025, Sec. 4.1; Supp. 7.4)
LiDARLivox Avia資料集感測器Botanic Gardensecond LiDAR on the Botanic Garden robot(Xie et al., 2025, Sec. 4.1)
LiDARLivox MID-360方法輸入未標示self-collected sequence 'private-360', images 640 x 512(Xie et al., 2025, Supp. 7.2)
LiDARHESAI Pandar XT-32歸入:Hesai PandarXT-32方法輸入未標示self-collected sequence 'private-pandar', images 640 x 512(Xie et al., 2025, Supp. 7.2)
慣性量測單元(IMU)Livox Avia built-in IMU資料集感測器R3LIVE dataset; FAST-LIVO dataset200 Hz(Xie et al., 2025, Sec. 4.1)
相機RGB camera (model not reported)資料集感測器R3LIVE dataset; FAST-LIVO dataset15 Hz, 640 x 512(Xie et al., 2025, Sec. 4.1)
相機camera (model not reported)資料集感測器NTU-VIRALimage resolution 752 x 480(Xie et al., 2025, Sec. 4.1)
相機camera (model not reported)資料集感測器Botanic Gardenimage resolution 480 x 300(Xie et al., 2025, Sec. 4.1)
載具平台wheeled robot資料集感測器Botanic Gardentraverses a botanic garden(Xie et al., 2025, Sec. 4.1)
載具平台handheld device資料集感測器R3LIVE dataset; FAST-LIVO datasetLivox Avia, built-in IMU and RGB camera(Xie et al., 2025, Sec. 4.1)
運算硬體Intel Core i9-13900HX執行運算平台未標示5.50 GHz CPU, 64 GB RAM desktop PC(Xie et al., 2025, Sec. 4.1 Implementation Details)
運算硬體NVIDIA RTX 4060 Laptop 8 GB GPU執行運算平台未標示8 GB(Xie et al., 2025, Sec. 4.1 Implementation Details; Sec. 4.3)

作者報告的優勢與限制

優勢

限制

營建工程相關證據

論文未在營建場域測試;資料為 R3LIVE、FAST-LIVO、NTU-VIRAL、Botanic Garden,以及作者以 Livox MID-360 與 HESAI Pandar XT-32 自錄的兩段序列。論文只評估渲染品質、資源用量與軌跡,未量測地圖幾何精度,因此無法直接支持營建量測用途。

原文驗證環境: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 64 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。

Xie et al., 2025 · Supp. Table 7 本方法 14 筆

表格設定(擷取紀錄原文):Tracking accuracy on Botanic Garden using Velodyne VLP-16 data; RPE and ATE over full transformations; units, statistic and alignment not stated; 'Ours' is the authors' improved SR-LIVO tracker without loop closure; arXiv v1 supplementary (Xie et al., 2025, Supp. Table 7)

RPE (full transformation),Botanic Garden · 1005 00

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 Xie 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:原文未報告;單位:原文未報告;場景:outdoor botanic garden, wheeled robot, Velodyne VLP-16

資料來源作者報告值(Xie et al., 2025, Supp. Table 7)

數值與出處
方法(原文寫法)報告值出處
R3LIVE [18]1.165(Xie et al., 2025, arXiv v1 Supp. Table 7)
FAST-LIO2 [43]1.048(Xie et al., 2025, arXiv v1 Supp. Table 7)
LVI-SAM [33]0.347(Xie et al., 2025, arXiv v1 Supp. Table 7)
OURS本方法原文提出0.174(Xie et al., 2025, arXiv v1 Supp. Table 7)

Xie et al., 2025 · Table 1 本方法 12 筆

表格設定(擷取紀錄原文):Rendering quality, mean over all observation images; reduced scenes of at most 100 frames and 5 min reconstruction; NeRF-SLAM, MonoGS and 3DGS given COLMAP poses and depth, GS-LIVM uses its own LIVO poses (Xie et al., 2025, Table 1)

PSNR,R3LIVE dataset · hku campus seq 00

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 Xie 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:平均值(mean);對齊方式:未對齊;單位:dB;場景:Livox Avia, handheld, HKU campus outdoor

資料來源作者報告值(Xie et al., 2025, Table 1)

數值與出處
方法(原文寫法)報告值出處
Nerf-SLAM [27]13.232 dB(Xie et al., 2025, Table 1)
MonoGS [21]12.142 dB(Xie et al., 2025, Table 1)
3DGS [13]21.744 dB(Xie et al., 2025, Table 1)
Ours本方法原文提出22.43 dB(Xie et al., 2025, Table 1)

Xie et al., 2025 · Table 2 本方法 12 筆

表格設定(擷取紀錄原文):Mapping time (MT) against sequence duration (DT), number of 3D Gaussians and maximum GPU memory for the full sequence, ns = 3 (Xie et al., 2025, Table 2)

Count of 3D Gaussians,R3LIVE dataset · hku campus seq 00

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 Xie et al., 2025 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:count;場景:outdoor

數值與出處
方法(原文寫法)報告值出處
Ours本方法原文提出硬體:Intel Core i9-13900HX (5.50 GHz), 64 GB RAM, NVIDIA RTX 4060 Laptop 8 GB GPU1209666 count(Xie et al., 2025, Table 2)

Xie et al., 2025 · Supp. Table 8 本方法 8 筆

表格設定(擷取紀錄原文):Ultra-long sequences with nr = 2: mapping time vs duration, peak memory and rendering metrics; arXiv v1 supplementary (Xie et al., 2025, Supp. Table 8)

Mem (Mb),R3LIVE or FAST-LIVO dataset (not stated) · hku main building

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 Xie et al., 2025 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:最大值(max);對齊方式:未對齊;單位:Mb (as written; megabytes or megabits not specified);場景:outdoor campus, Livox Avia

數值與出處
方法(原文寫法)報告值出處
Ours本方法原文提出硬體:Intel Core i9-13900HX (5.50 GHz), 64 GB RAM, NVIDIA RTX 4060 Laptop 8 GB GPU4489(Xie et al., 2025, arXiv v1 Supp. Table 8)

其他比較組

列出其餘 5 個比較組

來源

  • Xie et al., 2025

    Yusen Xie, Zhenmin Huang, Jin Wu, Jun Ma(2025)GS-LIVM: Real-Time Photo-Realistic LiDAR-Inertial-Visual Mapping with Gaussian Splatting2025 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 26869-26878

    同儕審查已出版已讀全文近十年

回到方法圖鑑

選擇開啟Esc關閉