Unlabeled egocentric video can be converted into obstacle-aware goal-conditioned navigation supervision through monocular geometry, ESDFs, and MPPI-planned trajectories.
isdf: Real-time neural signed distance fields for robot perception
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.RO 3years
2026 3representative citing papers
G-EDF-Loc models the Euclidean distance field as a block-sparse Gaussian mixture to enable real-time, gradient-based 6DoF localization that remains robust under severe odometry degradation or without IMU priors.
A hybrid structural latent points representation is learned by inserting a point-wise latent VAE into a point-cloud autoencoder and regularizing toward a Gaussian prior, paired with a lightweight 3DGS rendering pipeline, yielding gains on RLBench and ManiSkill2 benchmarks.
citing papers explorer
-
VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision
Unlabeled egocentric video can be converted into obstacle-aware goal-conditioned navigation supervision through monocular geometry, ESDFs, and MPPI-planned trajectories.
-
G-EDF-Loc: 3D Continuous Gaussian Distance Field for Robust Gradient-Based 6DoF Localization
G-EDF-Loc models the Euclidean distance field as a block-sparse Gaussian mixture to enable real-time, gradient-based 6DoF localization that remains robust under severe odometry degradation or without IMU priors.
-
Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
A hybrid structural latent points representation is learned by inserting a point-wise latent VAE into a point-cloud autoencoder and regularizing toward a Gaussian prior, paired with a lightweight 3DGS rendering pipeline, yielding gains on RLBench and ManiSkill2 benchmarks.