A reference-based geometric hashing method recovers cross-model vector correspondences by exploiting local isometric consistency in contrastive embeddings and iteratively bootstrapping from a seed of paired anchors.
Teaser: Fast and certifiable point cloud registration
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Picasso is an inference-time pose corrector that uses physics-constrained rejection sampling and a contact scene graph to make multi-object scene reconstructions physically plausible and often more accurate.
A deep RL vulnerability-prediction policy trained in semantic embedding space finds up to 23% more unique robot manipulation failures than vision-language baselines and enables more efficient fine-tuning.
Proposes SIME framework with AM and AM-SDR solvers for 3D rotation search and rigid point-set registration, claiming lower fitting residuals than MC-based methods on high-outlier data.
citing papers explorer
-
Vector Linking via Cross-Model Local Isometric Consistency
A reference-based geometric hashing method recovers cross-model vector correspondences by exploiting local isometric consistency in contrastive embeddings and iteratively bootstrapping from a seed of paired anchors.
-
Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling
Picasso is an inference-time pose corrector that uses physics-constrained rejection sampling and a contact scene graph to make multi-object scene reconstructions physically plausible and often more accurate.
-
RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields
A deep RL vulnerability-prediction policy trained in semantic embedding space finds up to 23% more unique robot manipulation failures than vision-language baselines and enables more efficient fine-tuning.
-
A Robust 3D Registration Method via Simultaneous Inlier Identification and Model Estimation
Proposes SIME framework with AM and AM-SDR solvers for 3D rotation search and rigid point-set registration, claiming lower fitting residuals than MC-based methods on high-outlier data.