MonoLift: Learning 3D Manipulation Policies from Monocular RGB via Distillation

NeurIPSSpotlight2025

Authors: Ziru Wang, Mengmeng Wang, Guang Dai, Yongliu Long, Jingdong Wang
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Although learning 3D manipulation policies from monocular RGB images is lightweight and deployment-friendly, the lack of structural information often leads to inaccurate action estimation…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

distillation 3d

← All NeurIPS 2025 Spotlight papers · Browse the whole archive