An offline LiDAR-inertial-thermal Gaussian splatting pipeline that anchors thermal-LiDAR associations on FAST-LIVO2 map points and injects LiDAR plane constraints into both bundle adjustment and Gaussian training.

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。

LIT-GS 的技術屬性
感測輸入3D LiDAR (Livox Avia, 10 Hz per Fig. 2)、IMU (built into the Livox Avia, 200 Hz per Fig. 2)、visible-light camera (MV-CA013-21UC)、long-wave thermal imager (MV-CI003-GL-N15, 10 Hz per Fig. 2)
原文測試平台handheld (inferred: the paper uses a modified version of a sensor suite whose repository is named LIV_handhold, and Fig. 1 shows battery, on-board PC and display; the carrying mode is not stated in the text)
狀態估計upstream FAST-LIVO2 LIV estimate, then offline LiDAR-plane-constrained bundle adjustment (extension of COLMAP-PCD) and differentiable Gaussian optimization
資料關聯learned thermal feature matching; uncertainty-tagged LIV visual map points as cross-modal anchors; weighted LiDAR point-to-plane residuals in BA and as a splatting regularizer
時間表示原文未報告 (PPS triggers from a microcontroller synchronize LiDAR, IMU and thermal camera; Fig. 1 a3 labels an STM32 board and GPRMC over USB serial)
去畸變原文未報告
迴圈閉合none reported
全域最佳化offline bundle adjustment over poses and triangulated points
地圖表示3D Gaussians (thermal), initialized from LiDAR voxel map and refined structure
先驗資訊upstream FAST-LIVO2 map points and poses
可輸出幾何thermal Gaussian map with rendered images; geometric consistency evaluated with Earth Mover's Distance to reference point clouds (Sec. IV-B2)
計算需求offline: training on one scene 70.6 min; rendering about 25.3 ms per 640x512 frame on i7-14700KF with RTX 4080D (Sec. IV-C)

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方法輸入未標示built-in IMU; 10 Hz (Fig. 2)(Shi et al., 2026, Sec. IV-A; Fig. 1; Fig. 2)
慣性量測單元(IMU)built-in IMU of the Livox Avia方法輸入未標示200 Hz (Fig. 2)(Shi et al., 2026, Sec. IV-A; Fig. 2)
相機MV-CA013-21UC visible-light camera資料集感測器authors' private thermal dataset (self-collected rig)原文未報告(Shi et al., 2026, Sec. IV-A)
熱像儀MV-CI003-GL-N15 long-wave thermal imager方法輸入未標示10 Hz (Fig. 2); rendering evaluated at 640 x 512 per frame (Sec. IV-C); native imager resolution not stated(Shi et al., 2026, Sec. IV-A; Sec. IV-C; Fig. 2)
運算硬體Intel Core i7-14700KF CPU執行運算平台未標示原文未報告(Shi et al., 2026, Sec. IV-A)
運算硬體NVIDIA GeForce RTX 4080D GPU執行運算平台未標示原文未報告(Shi et al., 2026, Sec. IV-A)
其他STM32 microcontroller (PPS synchronization board)方法輸入未標示synchronized timers, GPRMC over USB serial (Fig. 1 a3)(Shi et al., 2026, Sec. III; Fig. 1 (a3))

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(私人資料為 Car、Logo、Sundial、Tree-stump、Bushes 五個場景;公開資料為 M2DGR 的 Street-03、Gate-01、Lift-01、Door-02、Hall-02;未見工地)。熱影像與幾何正則化對夜間或低照度隧道檢測可能有參考價值(推論)。

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 2 個比較組,合計 50 筆紀錄。

Shi et al., 2026 · Table I 本方法 48 筆

表格設定(擷取紀錄原文):Thermal Gaussian-splatting reconstruction quality; private scenes captured with the authors' Livox Avia + thermal rig at different times of day (Fig. 3 caption lists 12:00 p.m. to 6:00 a.m.), public scenes are five M2DGR sequences; EMD reference point cloud source not described; Avg. columns printed by the authors (Shi et al., 2026, Table I)

PSNR (rendering fidelity, higher is better),authors' private thermal dataset · Car

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 Shi et al., 2026 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:dB (unit not printed);場景:outdoor private scenes under varied lighting

資料來源作者報告值(Shi et al., 2026, Table I)

數值與出處
方法(原文寫法)報告值出處
Ours本方法原文提出26.061(Shi et al., 2026, Table I)
Thermal3D-GS24.216(Shi et al., 2026, Table I)
LIV-GaussMap23.569(Shi et al., 2026, Table I)

Shi et al., 2026 · Text Sec.IV-C 本方法 2 筆

資料集與序列authors' private thermal dataset · Car

表格設定(擷取紀錄原文):Offline training and rendering cost (Shi et al., 2026, Text Sec.IV-C)

training time on the Car scene,authors' private thermal dataset · Car

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 Shi et al., 2026 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:min;場景:outdoor

數值與出處
方法(原文寫法)報告值出處
LIT-GS本方法原文提出硬體:Intel Core i7-14700KF CPU + NVIDIA GeForce RTX 4080D GPU70.6 min(Shi et al., 2026, Sec. IV-C)

來源

  • Shi et al., 2026

    Shikuan Shi, Chunran Zheng, Jiaming Xu, Tianyong Ye, Tao Yu, Yukang Cui(2026)LIT-GS: LiDAR-Inertial-Thermal Gaussian Splatting for Illumination-Robust MappingarXiv (author comment: accepted to IEEE/RSJ IROS 2026)

    已接受(作者聲明)已讀全文近十年查證後修正

回到方法圖鑑

選擇開啟Esc關閉