REVIEW 5 cited by
Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Visual imitation learning methods demonstrate strong performance, yet they lack generalization when faced with visual input perturbations, including variations in lighting and textures, impeding their real-world application. We propose Stem-OB that utilizes pretrained image diffusion models to suppress low-level visual differences while maintaining high-level scene structures. This image inversion process is akin to transforming the observation into a shared representation, from which other observations stem, with extraneous details removed. Stem-OB contrasts with data-augmentation approaches as it is robust to various unspecified appearance changes without the need for additional training. Our method is a simple yet highly effective plug-and-play solution. Empirical results confirm the effectiveness of our approach in simulated tasks and show an exceptionally significant improvement in real-world applications, with an average increase of 22.2% in success rates compared to the best baseline. See https://hukz18.github.io/Stem-Ob/ for more info.
Forward citations
Cited by 5 Pith papers
-
AffordGen: Generating Diverse Demonstrations for Generalizable Object Manipulation with Afford Correspondence
AffordGen synthesizes large-scale affordance-aware manipulation trajectories via keypoint correspondence on 3D meshes, enabling zero-shot visuomotor policies for unseen objects from few source demos.
-
SViP: Sequencing Bimanual Visuomotor Policies with Object-Centric Motion Primitives
SViP shows that sequencing a visuomotor policy with TAMP-planned primitives, via learned switching conditions and feasibility checks, improves generalization from few demonstrations in bimanual manipulation.
-
DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo
DenseMatcher combines 2D image features with a 3D neural network and functional maps to compute dense semantic correspondences between textured 3D objects, enabling single-demo cross-category robot manipulation.
-
DIPOLE: Fusing Vision and Geometry for Robust Visuomotor Generalization
Fusing RGB and point-cloud inputs with training-time modality dropout plus cross-attention makes a diffusion visuomotor policy markedly more robust to visual and spatial shifts than unimodal or naively fused baselines.
-
N2M: Bridging Navigation and Manipulation by Learning Pose Preference from Rollout
N2M predicts preferable base poses for manipulation policies from ego-centric point clouds, learned from rollouts, lifting success from 3% to 54% in the PnPCounterToCab task.
Discussion (0). Continue with ORCID to comment.