Streaming 3D Gaussian Splatting (3DGS) allows for online reconstruction of dynamic scenes from multi-view videos for Free Viewpoint Video (FVV). Current time and storage efficient methods rely on selecting a subset of anchor Gaussians and neighborhood interpolation for fast streamable 3DGS. However, these methods can overlook object-specific motion and introduce inconsistencies near object boundaries. We propose OCLDA-GS, an object-centric streaming framework that dynamically reallocates object and motion-aware Gaussian anchors to allocate anchor Gaussian support for objects undergoing large motion while at the same time, restricting the gaussian neighborhood within object groups for more precise object boundaries. Furthermore, it estimates object-wise rigid transformations (e.g. a hand moving) and leverages these estimates to learn per-anchor local deformation correction for small deformations (e.g. wrinkles on a shirt). Then, we conduct experiments on three dynamic multi-view video datasets and demonstrate improvements over the previous baselines alongside improved quality between refinement timesteps. Under matched refinement budgets, our method improves PSNR over Instant Gaussian Stream (IGS) by 0.169 dB on N3DV, 0.202 dB on Meeting Room and +0.199 on Google Immersive, while reducing the mean PSNR drop between refinement timesteps by 9.2% and 13.8% in N3DV and Meeting Room, respectively.
Figures & tables
Figure 4: Overview of our method. (a) Flow-guided anchor selection within object groups. (b) Object-wise rigid motion estimation from AGM-Net predictions. (c) Learned local deformation corrections propagated to Gaussians within each object. (d) Improved rendering quality compared to Farthest Point Sampling (FPS) -based IGS.
Method
# Params
# Online refinements
N3DV
Meeting Room
Google Immersive
Average
PSNR ↑
DSSIM ↓
s/frm ↓
PSNR ↑
DSSIM ↓
s/frm ↓
PSNR ↑
DSSIM ↓
s/frm ↓
PSNR ↑
DSSIM ↓
s/frm ↓
Offline methods
RT 4DGS [ 36 ]
0
32.010
0.014
30.470
0.025
26.760
0.030
29.747
0.023
4D-GS [ 33 ]
2.46M
31.150
0.016
31.275
0.024
23.990
0.079
28.805
0.040
STG [ 18 ]
90
32.050
0.026
29.510
0.034
29.200
0.042
30.253
0.034
Swift4D [ 34 ]
31.92M
32.230
0.014
31.306
0.022
23.482
0.060
29.006
0.032
Table 1: Quantitative comparison on N3DV, Meeting Room, and Google Immersive. Average is the equal-weight mean of the three displayed dataset results. Gray rows are offline methods; the remaining rows are online methods. Darker blue indicates the best, and second-best online results. Offline quality includes published reference results.
Figure 5: Qualitative comparison of online methods across three datasets. Each row uses the same frame, viewpoint, and crop for all methods. Orange boxes mark regions enlarged in the insets, highlighting motion alignment and object boundaries.
Figure 6: Flow-guided anchor selection and temporal propagation. Flow guides anchor reselection within a fixed budget. Colors denote SAGA groups; white points mark selected anchors. Markers and trails visualize anchor and Gaussian motion. Ours shows the refined target keyframe from an input-camera view. Reselection and refinement occur only at keyframes.
Object
Flow
LD
N3DV
Meeting Room
Average
PSNR ↑
DSSIM ↓
s/frm ↓
PSNR ↑
DSSIM ↓
s/frm ↓
PSNR ↑
DSSIM ↓
s/frm ↓
×
×
×
32.877
0.020
2.00
30.088
0.028
1.96
31.482
0.024
1.98
✓
×
×
32.882
0.020
2.20
30.116
0.028
2.14
31.499
0.024
2.17
×
✓
×
32.913
0.020
2.37
30.263
0.027
2.31
31.588
0.023
2.34
×
×
✓
33.059
0.020
2.28
30.109
0.028
2.24
31.584
0.024
2.26
✓
✓
×
32.927
0.020
2.33
30.267
0.027
2.27
31.597
0.023
2.30
Table 2: Component ablation on N3DV and Meeting Room. Checkmarks indicate enabled components. The first row corresponds to IGS (FPS), and the last row to our full method. Average equally weights the two datasets. LD: Local Deformation
Configuration
PSNR ↑
Average
N3DV
MR
PSNR ↑
DSSIM ↓
Local deformation configuration
No correction
32.927
30.267
31.597
0.023
Rigid replacement
32.988
30.204
31.596
0.024
LD MLP w/o Rigid
32.991
30.280
31.636
0.023
Anchor Reallocation
Table 3: Ablation of local deformation and anchor allocation on N3DV and Meeting Room (MR). Average metrics equally weight the two datasets. LD: Local Deformation
Figure 7: Temporal reconstruction quality with selected online baselines. Faint traces show raw values; solid curves show a 45-frame EMA. Full comparisons appear in Tab. 1 .
Figure 8: Mean PSNR drop relative to keyframes on N3DV and Meeting Room; lower is better.
Table 4: Motion-anchor budget ablation across the datasets. PSNR ( ↑ ) averages evaluated targets per scene, followed by an equal-scene average within each dataset. Shading indicates the highest PSNR per dataset.