16 papers
GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors
Tianyi Xie, Haotian Zhang, Jinhyung Park +17
Scaling humanoid loco-manipulation requires robot-compatible demonstrations across diverse objects, whole-body motions, and scene geometries, but teleoperation and motion capture a…
Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning
Jixuan He, Xueting Li, Chieh Hubert Lin +1
Vision-Language Models (VLMs) exhibit emerging spatial reasoning capabilities, yet they remain unreliable on tasks requiring precise spatial understanding, such as viewpoint reason…
Gaga: Group Any Gaussians via 3D-aware Memory Bank
Weijie Lyu, Xueting Li, Abhijit Kundu +2
We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot class-agnostic segmentation models. Co…
SOMA: Unifying Parametric Human Body Models
Jun Saito, Jiefeng Li, Michael de Ruyter +12
Parametric human body models are foundational to human reconstruction, animation, and simulation, yet they remain mutually incompatible: SMPL, SMPL-X, MHR, Anny, and related models…
ReCoSplat: Autoregressive Feed-Forward Gaussian Splatting Using Render-and-Compare
Freeman Cheng, Botao Ye, Xueting Li +3
Online novel view synthesis remains challenging, requiring robust scene reconstruction from sequential, often unposed, observations. We present ReCoSplat, an autoregressive feed-fo…
Edit3r: Instant 3D Scene Editing from Sparse Unposed Images
Jiageng Liu, Weijie Lyu, Xueting Li +2
We present Edit3r, a feed-forward framework that reconstructs and edits 3D scenes in a single pass from unposed, view-inconsistent, instruction-edited images. Unlike prior methods…