Zhenjun Zhao

ericzzj.bsky.social

30 May 2025 21:55

4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians Hidenobu Matsuki, Gwangbin Bae, @ajdavison.bsky.social tl;dr: 2DGS->scene; coordinate-based network->deformation; new synthetic dataset of dynamic objects arxiv.org/abs/2505.22859

Chris Paxton

cpaxton.bsky.social

08 April 2025 09:42

Ideally, when I unbox a new robot, I just want to teach it the way I would my kid, by giving it a couple demonstrations -- not by teleop, not by endless prompt engineering. So, how can we use human videos to teach robots how to perform tasks in new environments? www.robot-learning.uk/r-plus-x

Keenan Crane

keenancrane.bsky.social

28 March 2025 11:27

Stupid #Keynote trick: if you want the math font to match the text font, write expressions like \𝚝𝚎𝚡𝚝{𝚞}_\𝚝𝚎𝚡𝚝{𝚒} rather than just 𝚞_𝚒 when inserting equations. [Wish this were just the default behavior…]

Zhenjun Zhao

ericzzj.bsky.social

28 March 2025 07:35

Can Video Diffusion Model Reconstruct 4D Geometry? Jinjie Mai, Wenxuan Zhu, Haozhe Liu, Bing Li, Cheng Zheng, Jürgen Schmidhuber, Bernard Ghanem tl;dr: pretrained video VAE->finetune pointmap VAE; finetune Open-Sora within latent space of video&pointmap arxiv.org/abs/2503.21082

Zhenjun Zhao

ericzzj.bsky.social

28 March 2025 07:35

GenFusion: Closing the Loop between Reconstruction and Generation via Videos Sibo Wu, Congrong Xu, Binbin Huang, @andreasgeiger.bsky.social, Anpei Chen tl;dr: reconstruction-driven video generation architecture->artifact-prone renderings->video arxiv.org/abs/2503.21219