Search papers, labs, and topics across Lattice.
The paper introduces GenSplat, a novel feed-forward 3D Gaussian Splatting framework for view-generalized robotic policy learning. GenSplat reconstructs high-fidelity 3D scenes from sparse, uncalibrated inputs using a permutation-equivariant architecture and a 3D-prior distillation strategy to prevent geometric collapse. By rendering diverse synthetic views from the reconstructed 3D scenes, GenSplat augments the observational manifold during training, leading to policies that generalize better to novel viewpoints.
Policies trained with GenSplat maintain robust performance under severe spatial perturbations where baseline methods completely fail, thanks to its novel 3D Gaussian Splatting-based augmentation.
Prevailing 2D-centric visuomotor policies exhibit a pronounced deficiency in novel view generalization, as their reliance on static observations hinders consistent action mapping across unseen views. In response, we introduce GenSplat, a feed-forward 3D Gaussian Splatting framework that facilitates view-generalized policy learning through novel view rendering. GenSplat employs a permutation-equivariant architecture to reconstruct high-fidelity 3D scenes from sparse, uncalibrated inputs in a single forward pass. To ensure structural integrity, we design a 3D-prior distillation strategy that regularizes the 3DGS optimization, preventing the geometric collapse typical of purely photometric supervision. By rendering diverse synthetic views from these stable 3D representations, we systematically augment the observational manifold during training. This augmentation forces the policy to ground its decisions in underlying 3D structures, thereby ensuring robust execution under severe spatial perturbations where baselines severely degrade.
