Open Source
LightSEAD: Lightweight SE(3)-Aware Keypoint Detector through Selective Knowledge Distillation
arXiv cs.RO0 views
arXiv:2611.23661v1 Announce Type: cross Abstract: The pursuit of improved performance in deep learning has often been accompanied by increasing architectural complexity and computational demands. We explore an alternative direction: achieving more with less through structured supervision. We introduce LightSEAD, a lightweight SE(3)-aware keypoint detector initialised with calibrated Harris pseudo-labels and enriched through viewpoint-aware and appearance-aware supervision and selective knowledge distillation. LightSEAD comprises only six convolutional layers and 84,289 learnable parameters, achieving competitive repeatability across HPatches, KITTI 06 and 4Seasons while demonstrating its downstream applicability to relative pose estimation on MegaDepth-1500. Further optimised for mixed-precision inference, LightSEAD Coarse achieves approximately 909 FPS on an NVIDIA RTX 4090 and 139 FPS on a Jetson Orin Nano Super.
Source:https://arxiv.org/abs/2611.23661PreviousDOCK: Dual-Stream-Inspired Self-Supervised Object-Centric Representations Grounded in Robot KinematicsNextRoboBuilder: Agentic Robot Co-Design with Real-world Video Feedback in the Loop
Related posts
DrawScore: Evaluating Generated CAD Models against Engineering Drawings
0arXiv cs.SE
Predicting Process-Level Behavior: A Benchmarking Study
0arXiv cs.SE
Characterizing GitHub Security Actions Alerts For Web Application Tutorials
0arXiv cs.SE
AeroRSI: Recursive Self-Improvement for Aerial Vision-Language Navigation
0arXiv cs.RO
RoboBuilder: Agentic Robot Co-Design with Real-world Video Feedback in the Loop
0arXiv cs.RO
Render the Robot, Generate the World: One Video World Model Across Embodiments
0arXiv cs.RO