Visibility-Aware Reference Generation for Benchmarking Visual 3D Reconstruction in Vegetation-Rich Environments

Zhipeng Zhong; Matthew Coombes; Cunjia Liu

cs.CVNov 3, 2026

Visibility-Aware Reference Generation for Benchmarking Visual 3D Reconstruction in Vegetation-Rich Environments

Authors: Zhipeng Zhong, Matthew Coombes, Cunjia Liu

Organizations: Department of Aeronautical and Automotive Engineering, Loughborough University, Leicestershire, UK, LE11 3TU

Abstract

Reliable evaluation of visual 3D reconstruction and depth estimation in vegetation-rich outdoor environments is limited by the scarcity of geometric ground-truth data and the cost of complete scanner surveys. We present a LiDARbased reference-generation pipeline for evaluating the zero-shot performance of feed-forward visual-geometry models alongside conventional structure-from-motion (SfM) methods. The pipeline reuses camera images, LiDAR scans, and reference poses from existing multi-sensor localization datasets to generate per-view depth maps and visible reference point clouds. To address visibility errors in accumulated LiDAR scans, we introduce the LargeDepth-Gap Visibility Score (LDGVS) for point-wise visibility filtering and automatic scale selection in Hidden Point Removal(HPR). Experiments on TartanAirV2 and TartanGround show that, compared with Poisson surface reconstruction, which is an approach suited to completed scan surveys, the combined HPR and LDGVS filtering retains approximately three times the point density at comparable absolute relative error. We also apply the pipeline to the BotanicGarden dataset to systematically compare depth estimation and 3D reconstruction methods. Feedforward methods produce dense depth predictions efficiently, but their 3D reconstructions can contain duplicated structures. Conventional SfM generally produces more coherent geometry, but its reconstructions remain sparse and more prone to failure in challenging vegetated scenes. The benchmark toolkit and datasets will be released.

Figures & tables

Fig. 1: Visualization of the reference data generated by the proposed pipeline in BotanicGarden. Top: the accumulated scene-level reference point cloud and the camera trajectory shown in red. The colored boxes indicate the two individual-view examples below. Bottom: for each example, the upper row shows the corresponding visibility-filtered point cloud in the camera frame, and the lower row shows the projected sparse reference depth image.

Dataset	GT Trajectory	Data Scale
SFU-Mountain [ 31 ]	Manually aligned locations	$>$ 8 h, 150 GB
RELLIS-3D [ 32 ]	VoxNet poses	5 seq., 13.6k scans
Wild-Places [ 33 ]	Wildcat SLAM poses	8 seq., 63k submaps
TreeScope [ 34 ]	Faster-LIO poses	6 sites, $>$ 1.8k labels
CitrusFarm [ 35 ]	GPS-RTK	7 seq., 1.7 h, 1.3 TB
ARD-VO [ 36 ]	GPS-RTK	11 sessions, $>$ 1 TB

TABLE I: Multi-sensor localization datasets in vegetation-rich outdoor environments.

Fig. 2: Overview of the LiDAR-based reference-generation pipeline. In the “Deskew and denoise” step, the retained point cloud is shown in green and the raw point cloud in red.

Panel of Figure 4 — Fig. 3: Examples of the visibility problem in single-scan and accumulated LiDAR point clouds. Background points are projected onto foreground tree regions, producing incorrect occlusion relationships.

Panel of Figure 5 — Fig. 4: Examples of local depth histograms constructed from the 75 nearest projected LiDAR samples. Correct projections, such as the middle example, produce no distinct depth gap, whereas incorrect projections, such as the left and right examples, produce a clear gap.

Panel of Figure 6 — Fig. 5: Effect of the HPR radius scale in close-range (top row) and far-range (bottom row) scenes. Results are shown for $s=500$ (left column) and $s=5000$ (right column). A scale that gives an acceptable visibility estimate at close range can retain many incorrect depth samples at long range, motivating automatic radius scale selection.

Method	AbsRel $\downarrow$	Rel $\tau$ $\uparrow$	Abs $\downarrow$	Abs $\tau$ $\uparrow$	Density $\uparrow$
Single scan (left view)	0.1138	0.7782	3.7065	0.4652	0.0232
Single scan (right view)	0.4024	0.7448	4.2277	0.4030	0.0216
Cumulation (baseline)	0.4016	0.6384	5.4760	0.3098	0.2524
Cumulation+CP	0.3214	0.6393	5.5628	0.3176	0.3171
PSR	0.1386	0.7336	3.2805	0.4297	0.0582
SGM	0.3093	0.5919	3.6819	0.2426	0.0065

TABLE II: Evaluation of visible depth on TartanAirV2 Data_easy and TartanGround Data_omni. The best value per metric is shown in bold and the second-best distinct value is underlined.

Panel of Figure 8 — Fig. 6: Qualitative comparison of visible-depth projections for a TartanAirV2 forest scene. Panels (a) and (b) show the right-view RGB image and ground-truth depth, respectively; panels (c)–(l) show the projections generated by the selected comparison and proposed methods.

Feed-forward dense reconstruction
Method	Filter	Align	Seq.	Acc $\downarrow$	Acc $\tau$ $\uparrow$	Comp $\downarrow$	Comp $\tau$ $\uparrow$	CD $\downarrow$	F1 $\uparrow$	Density $\uparrow$	Runtime $\downarrow$
VGGT [ 17 ]	–	$\checkmark$	10/10	0.3136	0.2719	0.6837	0.4106	0.9973	0.3236	1.0000	0.0508
VGGT [ 17 ]	P50	$\checkmark$	10/10	0.1059	0.4587	1.4361	0.2845	1.5421	0.3486	0.5018	0.0503
VGGT- $\Omega$ [ 18 ]	–	$\checkmark$	10/10	0.2753	0.3442	0.2171	0.4848	0.4924	0.4015	1.0000	0.0287
VGGT- $\Omega$ [ 18 ]	P50	$\checkmark$	10/10	0.0639	0.6100	1.0890	0.3325	1.1529	0.4282	0.5000	0.0284
DA3 [ 19 ]	–	$\checkmark$	10/10	0.3311	0.2462	0.3967	0.3998	0.7278	0.3036	1.0000	0.0539

TABLE III: Quantitative comparison of selected 3D reconstruction methods. Within each method block, the best value per column, except Density, is in bold and the second-best distinct value is underlined; The Align column indicates whether scene-level point-cloud alignment is applied before evaluation. In method labels, K denotes the calibrated-intrinsics-only configuration, and S denotes the calibrated-stereo configuration. All methods in the SfM block use calibrated intrinsics. The Filter column identifies confidence-P50 masking (P50); a dash indicates that this operation is not applied. The Seq. column reports the number of successfully evaluated sequences.

Panel of Figure 10 — Fig. 7: Qualitative 3D reconstruction comparison on BotanicGarden_1006-03 . Columns show four fixed viewpoints of the same scene. The first row is the reference point cloud, followed by the feed-forward and SfM reconstruction methods. All methods use monocular input. VGGT, VGGT- $\Omega$ , DA3, MapAnything, and MASt3R-SfM are shown with confidence-P50 masking. All predictions are shown after alignment to the reference coordinate frame.

Monocular depth estimation
Method	Filter	Align	Abs $\downarrow$	Abs $\tau$ $\uparrow$	AbsRel $\downarrow$	Rel $\tau$ $\uparrow$	Density $\uparrow$	Runtime $\downarrow$
DA2 (Relative) [ 69 ]	–	$\checkmark$	3.9086	0.0090	0.4332	0.0392	0.9410	0.0160
DA2 (Metric) [ 69 ]	–	$\times$	11.3001	0.0001	2.0257	0.0041	1.0000	0.0157
DA2 (Metric) [ 69 ]	$\leq 10$ m	$\times$	5.2689	0.0000	1.9307	0.0002	0.2693	0.0158
DA2 (Metric) [ 69 ]	–	$\checkmark$	2.3071	0.0234	0.2497	0.0940	1.0000	0.0157
DA2 (Metric) [ 69 ]	$\leq 10$ m	$\checkmark$	0.2159	0.1360	0.0761	0.3486	0.2693	0.0158

TABLE IV: Quantitative comparison of depth-estimation methods. Within each method block, the best value per column, except Density, is in bold and the second-best distinct value is underlined; The Align column indicates whether per-frame affine depth alignment is applied before evaluation. In method labels, K denotes camera intrinsics and P denotes camera poses; The Filter column identifies confidence-P50 masking (P50) or the range restriction (

\leq 10

m); a dash indicates that neither operation is applied.

Panel of Figure 12 — Fig. 8: Qualitative dense-depth comparison on BotanicGarden_1006-01 . Full Depth shows the complete valid prediction for assessing relative-depth discrimination, whereas Filtered Depth shows the subset retained by method-specific confidence or range filtering. 3D View 1 and 3D View 2 show two fixed views of the point clouds, back-projecting the retained depth maps, and accumulating them across the sequence using the camera poses associated with each configuration. The first row contains, from left to right, the undistorted input image, reference depth, and two views of the reference point cloud; the remaining rows show the monocular, stereo, and multi-view depth-estimation methods.

LDGVSF threshold ablation
Method	AbsRel $\downarrow$	Rel $\tau$ $\uparrow$	Abs $\downarrow$	Abs $\tau$ $\uparrow$	Density $\uparrow$
Cumulation (baseline)	0.4016	0.6384	5.4760	0.3098	0.2524
LDGVSF(0.5)	0.2268	0.6837	4.4518	0.3368	0.2148
LDGVSF(0.7)	0.1819	0.6918	4.3071	0.3477	0.1944
LDGVSF(0.9)	0.1478	0.6915	4.2159	0.3569	0.1684
AHPR target low-visibility ratio and LDGVSF threshold ablation

TABLE V: Ablation study of LDGVSF thresholds and AHPR target low-visibility ratios on TartanAirV2 Data_easy and TartanGround Data_omni. The percentage in AHPR denotes the target low-visibility ratio

\rho^{\star}

. Within each ablation block, the best value per metric is shown in bold and the second-best distinct value is underlined.

Panel of Figure 14 — Fig. 9: Qualitative comparison of the unfiltered cumulation baseline and AHPR results with and without LDGVSF-based filtering of low-visibility-score points.

Panel of Figure 15 — Fig. 10: Qualitative comparison of visible-depth projections generated from Livox LiDAR data for BotanicGarden sequence 1018-13 . Panel (a) shows the right-view RGB image; panels (b)–(k) show the projections generated by the selected comparison and proposed methods.

Panel of Figure 16 — Fig. 11: Reference image and per-pixel depth-error maps for the TartanAirV2 forest scene. Panel (a) shows the right-view RGB image, and panel (b) shows the aligned left-view single-scan error. Panels (c)–(l) show the right-view errors for the ten projections in Fig. 6 (c)–(l), in the same order. Errors are displayed with a jet color map (blue: low error; red: high error).

Panel of Figure 17 — Fig. 12: Reference outputs for the ten BotanicGarden benchmark sequences. Columns 1–2 show two 3D views of the colorized reference point clouds; columns 3–4 show two colorized reference depth.

3D Reconstruction

3D reconstruction recovers a scene’s shape, appearance, and camera motion from images, video, depth, or other sensor measurements.

See all 971 papers

MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision
Oct 8, 2026Xinzhe Wang, Changjian Jiang, Kaiwen Song +8Feed-Forward 3D Reconstruction Camera Pose Estimation
Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · The University of Hong Kong +4
ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views
Aug 28, 2026Giuseppe Stracquadanio, Kevin Raj, Julia Grabinski +1Feed-Forward 3D Reconstruction Novel View Synthesis
TU Darmstadt · Zuse School ELIZA
ZVeC: A Zero-Shot Framework for Instance-Level Vehicle Extraction and Generative Point Cloud Completion
Sep 21, 2026Daisy Li, Kyle Gao, Quanyun Wu +3Point Cloud Completion 3D Scene Completion
University of Waterloo · Karlsruhe Institute of Technology

Oct 8, 2026J/K move · Enter open · S save

MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision

Xinzhe Wang, Changjian Jiang, Kaiwen Song, Xudong Li+7

Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · The University of Hong Kong+4

Feed-Forward 3D Reconstruction Camera Pose Estimation Indoor Scene Reconstruction 3D Gaussian Splatting

Open paper AskPDF arXiv

Feed-forward 3D priors enable high-quality reconstruction from image streams but often lack reliable metric scale and suffer from long-term trajectory drift. In contrast, LiDAR--inertial estimation provides metrically accurate motion but lacks the image-space consistency needed for high-fidelity reconstruction. We propose

MIRAGE

, which anchors feed-forward visual geometry to LiDAR--IMU metric motion and regulates online pose corrections according to correspondence support and cross-modal agreement, jointly enabling accurate metric pose estimation and high-fidelity Gaussian reconstruction. Experiments on Oxford Spires, M2DGR and INS show that MIRAGE achieves accurate metric trajectory estimation, outperforming COLMAP, a widely used but computationally expensive reference for vision-only benchmarks. Motivated by the scarcity of long-horizon monocular benchmarks for large-scale indoor reconstruction, we further build a multimodal data-collection platform and use MIRAGE to establish accurate 6-DoF reference trajectories for a new vision-only benchmark. We benchmark recent monocular large-scale reconstruction methods on this dataset, providing a systematic evaluation of their performance in long-horizon indoor scenes.

Abstract

3D Reconstruction

Explore similar work

MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision

ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views

ZVeC: A Zero-Shot Framework for Instance-Level Vehicle Extraction and Generative Point Cloud Completion