Jinwoo Shin, Pieter Abbeel, Kimin Lee, Stephen James, Younggyo Seo, Junsu Kim
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Visual robotic manipulation research and applications often use multiple cameras, or views, to better perceive the world. How else can we utilize the richness of multi-view data? In this paper, we investigate how to learn good representations with multi-view data and utilize them for visual robotic manipulation. Specifically, we train a multi-view masked autoencoder which reconstructs pixels of randomly masked viewpoints and then learn a world model operating on the representations from the autoencoder. We demonstrate the effectiveness of our method in a range of scenarios, including multi-view control and single-view control with auxiliary cameras for representation learning. We also show that the multiview masked autoencoder trained with multiple randomized viewpoints enables training a policy with strong viewpoint randomization and transferring the policy to solve real-robot tasks without camera calibration and an adaptation procedure. Video demonstrations are available at: https: //sites.google.com/view/mv-mwm.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.02408")
get_code_for_paper("2302.02408")
have("2302.02408")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2302.02408.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2302.02408)
Connect an agent — have() is free.