Visuomotor policies trained through imitation learning are highly sensitive to changes in camera viewpoint. This is particularly problematic for mobile manipulation (MoMa), where robots rarely execute manipulation from the exact same base pose used during demonstration collection due to navigation uncertainty, localization drift, and environmental constraints. Recent approaches use novel-view synthesis (NVS) to augment demonstrations with unseen viewpoints, but they assume static scenes and therefore fail to re-render the manipulated object during the post-contact interaction phase, leaving the most critical parts of the demonstration unaugmented. We present MOMASPLAT, a novel-view demonstration augmentation framework for mobile manipulation that synthesizes full manipulation trajectories from unseen robot base poses, including dynamic object interactions. Our key insight is that standard MoMa data collection naturally provides the multiview observations needed to reconstruct both the static scene and the manipulated object in 3D. MOMASPLAT combines 3D Gaussian Splatting, feed-forward 3D foundation models, and kinematics-based action retargeting to separately reconstruct the scene and manipulated object, render them from novel viewpoints, and generate geometrically consistent synthetic demonstrations paired with transformed actions. We evaluate MOMASPLAT on five real-world mobile manipulation tasks involving both rigid and articulated objects across three scenes, and validate the fidelity of its synthesized demonstrations against ground truth in simulation. MOMASPLAT substantially improves robustness to unseen base poses, more than doubling the average success rate of the strongest baseline and maintaining non-trivial success at large base displacements where all baselines fail, while reducing the need for largescale real-world data collection.
Figures & tables
Fig. 1 : MoMaSplat . Starting from mobile-manipulation data collected at the original base pose (white and red robot), MoMaSplat synthesizes demonstrations from sampled novel base poses ( yellow -outlined gray robot). The top-right sequence shows the source manipulation demonstration, while the bottom-right shows the corresponding synthesized trajectory, including the dynamic object as it is moved by the robot. Augmenting the source manipulation dataset with these demonstrations enables execution from unseen deployment-time base poses ( blue -outlined gray robot).
Fig. 2 : Overview of MoMaSplat . 3D Reconstruction: We build 3D models of the environment from the navigation and manipulation data. We estimate camera poses via structure-from-motion and fit a 3D Gaussian Splatting model of the static scene, Gscene . For the dynamic objects, we segment each manipulated object and estimate its per-frame pose trajectory with a feed-forward 3D foundation model; since the scene and object poses lie in separate reference frames, we align them with a Sim(3) transformation and fit a separate object model Gobj . Synthesizing Demonstrations from Unseen Base Poses: Given a robot base pose, T~ , sampled around the original demonstration poses (left), we render the scene and object from the new viewpoint, transform the source end-effector trajectory into the new base frame to render the robot from a simulator, and composite the three streams into a photorealistic novel observation. Paired with the transformed actions a~1:Lj , this forms a synthetic demonstration; repeating across sampled poses yields the generated dataset. Imitation Learning: the policy is trained on the union of source and generated demonstrations.
Fig. 3 : Tasks and scenes used in our experiments. We evaluate MoMaSplat on five real-world manipulation tasks across three scenes (top: scenes; bottom: per-task close-ups), covering manipulation of both rigid and articulated objects. The simulated scene and its task, Sim Pick-Place Bottle (right of the dashed lines), are used to measure the fidelity of MoMaSplat ’s generated demonstrations against ground truth.
Fig. 4 : Policy success across base poses. For each task, we evaluate 12 unseen base locations distributed across categorical distance bins that vary per task, with 3 trials per pose, and report success rate by distance to the nearest demonstration pose. The shaded gray region denotes the original base poses; locations 5–50 cm away are unseen deployment poses. MoMaSplat maintains substantially higher success as the base pose shifts away from the source demonstrations (where Source Only is labeled “Original data only”).
Fig. 5 : Spatial distribution of policy evaluation poses. Top-down view of each task showing the table and target-object locations, the original demonstration base poses, and the test base poses used for policy evaluation. Original demonstration poses are marked with circles, while evaluation poses are marked with squares; arrows indicate the robot heading at each pose. Evaluation poses are colored by MoMaSplat policy success rate, providing spatial context for the distance-based results in Fig. 4 .
Region
PSNR (dB) ↑
SSIM ↑
LPIPS ↓
Full image
21.27±1.12
0.902±0.019
0.253±0.030
Scene
26.40±2.18
0.936±0.021
0.248±0.037
Object
18.18±2.15
0.688±0.081
0.341±0.106
Robot
17.43±1.30
0.812±0.057
0.287±0.048
TABLE I : Generated-observation fidelity against simulator ground truth. Mean ± std over 75 generated demonstrations spanning viewpoints with distances of 0.4 – 27.3 cm from the reconstruction views. Full image , object , and robot use every tenth frame ( 2486 total frames), with object and robot restricted to their masks; scene PSNR evaluation uses one frame per demonstration ( 75 in total).
Stage
Parameter
Value
Scene SfM
matcher
sequential (COLMAP)
Scene 3DGS
method / iterations
WildGaussians / 30,000
Scene 3DGS
DSSIM weight
0.2
Metric scale
valid-depth range
(0,9] m, ≥1000 px/frame
Segmentation
detector / tracker
GroundingDINO / SAM2
Frame selection
IoU thresh. / max gap
0.8 / 20 frames
TABLE II : Key hyperparameters across the M o M a S plat pipeline.