Active 3D Gaussian reconstruction fundamentally relies on selecting informative next-best views under limited sensing budgets. Existing active 3DGS methods primarily plan viewpoints according to geometric information gain, treating object-induced hidden regions in the same manner as general unexplored space. Under tight frame budgets, such geometry-driven strategies may prioritize global scene coverage while leaving partially observed objects incompletely reconstructed. To address this limitation, we propose OccamView, an object-conditioned view-selection framework for frame-budgeted active 3D Gaussian reconstruction. Rather than predicting unseen object geometry or performing shape completion, OccamView maintains an online object memory from open-vocabulary detections grounded in measured RGB-D observations and represents unresolved local occupancy around detected objects as conservative hidden-region proxies. Candidate viewpoints are then evaluated using an occlusion-aware proxy-coverage score. Furthermore, we introduce a Geo-Floor mechanism that restricts object-conditioned re-ranking to geometrically competitive candidates, allowing object-conditioned cues to guide complementary observations while preserving the geometry-driven exploration behavior of the underlying planner. Experiments on Replica and Matterport3D under a unified frame-budgeted protocol show that OccamView consistently reduces Completion and improves Completion Ratio across five frame budgets, with particularly pronounced gains under limited frame budgets. These results demonstrate that lightweight object-conditioned cues effectively complement geometry-driven active view planning.
Figures & tables
Figure 1: Performance comparison between ActiveGAMER and OccamView on MP3D across frame budgets, showing a qualitative reconstruction example, Completion Ratio (C.R.) curves, and OccamView’s absolute gains in C.R. (pp) and Completion reduction (cm).
Figure 2: OccamView performs object-conditioned view selection for frame-budgeted active 3DGS reconstruction. It constructs an online object memory from open-vocabulary detections and measured RGB-D observations, and uses nearby unknown ( unk ) voxels as conservative hidden-region proxies. Candidate views are evaluated by occlusion-aware proxy coverage, while a geo-floor restricts re-ranking to geometrically competitive candidates before the combined geometric and proxy-coverage score selects the next view.
Method
Comp. (cm) ↓
C.R. (%) ↑
Acc. (cm) ↓
Replica, f40
Baseline
28.52
55.5
1.005
Ours
16.28 (↓12.24)
63.8 (↑8.3)
0.986 (↓0.019)
Replica, f80
Baseline
9.04
73.2
0.991
Ours
5.07 (↓3.97)
80.1 (↑6.9)
1.028 (↑0.037)
Table 1: Main results on Replica. Mean performance over eight scenes under matched frame budgets. Parenthesized values indicate absolute changes relative to the ActiveGAMER baseline.
Figure 3: Qualitative comparison on Replica under the f80 frame budget. Green and red denote reconstructed and missing ground-truth points, respectively. The right column highlights regions additionally recovered by OccamView compared with ActiveGAMER (magenta); gray denotes regions reconstructed by both methods. (a) room0, (b) room2, and (c) office4.
Method
Comp. (cm) ↓
C.R. (%) ↑
Acc. (cm) ↓
MP3D, f40
Baseline
84.55
31.8
2.875
Ours
78.45 (↓6.10)
32.3 (↑0.5)
2.835 (↓0.040)
MP3D, f80
Baseline
58.83
42.3
2.851
Ours
53.71 (↓5.12)
44.6 (↑2.3)
2.911 (↑0.060)
Table 2: Main results on MP3D. Mean performance over five real-world scenes under matched frame budgets. Parenthesized values indicate absolute changes relative to the ActiveGAMER baseline.
Figure 4: Qualitative comparison of reconstruction completeness on MP3D under the f160 frame budget. Green and red denote covered and missing ground-truth points under the 5 cm completion threshold, respectively. The right column highlights regions additionally recovered by OccamView compared with ActiveGAMER, while gray denotes regions recovered by both methods. (a) HxpKQynjfin, (b) pLe4wQe7qrG, and (c) GdvgFV5R1Z5.
Figure 5: Object-level reconstruction visualization. Representative MP3D objects comparing ActiveGAMER and OccamView. Gray denotes the ground-truth surface. Red indicates surfaces reconstructed by ActiveGAMER, whereas green and magenta denote surfaces reconstructed by OccamView, with magenta highlighting regions additionally recovered by OccamView.
Replica
MP3D
τ
Acc. (cm) ↓
Comp. (cm) ↓
C.R. (%) ↑
Acc. (cm) ↓
Comp. (cm) ↓
C.R. (%) ↑
0.00
1.146
6.45
84.2
2.593
21.46
61.0
0.70
1.137
2.87
89.2
2.493
16.91
61.6
0.85 (Ours)
1.117
2.95
88.7
2.272
14.72
63.2
0.95
1.080
3.36
87.0
2.322
14.52
64.4
Table 3: Ablation on the geo-floor threshold τ at frame budget B=160 over five seeds. Accuracy and Completion are reported in cm, and Completion Ratio is measured at 5 cm. Boldface and underlining indicate the best and second-best results in each column, respectively.
Comp. (cm) ↓
C.R. (%) ↑
Scene
Baseline
Ours
Δ
Baseline
Ours
Δ
office0
8.41
3.06
−5.35
76.0
84.9
+8.9
office1
3.91
2.79
−1.12
83.8
86.7
+2.9
office2
8.77
7.06
−1.71
72.9
74.7
+1.8
office3
7.12
6.59
−0.53
71.3
73.2
+1.9
office4
7.79
6.63
−1.16
73.2
76.8
+3.6
Table 4: Per-scene results on Replica under the f80 frame budget, averaged over five random seeds.
Variant
Object Comp. (cm) ↓
Scene C.R. (%) ↑
w/o object proxy
16.18
61.6
Random-center proxy
10.32
62.2
Detected-box proxy (Ours)
9.83
63.2
GT-box proxy
10.11
67.0
Table 6: Ablation on proxy localization on five MP3D scenes. Object Comp. measures the mean reconstruction distance on ground-truth object surfaces, while Scene C.R. measures full-scene coverage within 5 cm.
College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China · School of Software, Shandong University, Jinan, China · School of Data Science and Engineering, East China Normal University, Shanghai, China