13 papers
Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic Segmentation
Xuweiyi Chen, Wentao Zhou, Aruni RoyChowdhury +1
While massively scaling both data and models have become central in NLP and 2D vision, their benefits for 3D point cloud understanding remain limited. We study the initial step of…
WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments
Xuweiyi Chen, Wentao Zhou, Zezhou Cheng
We present WildRayZer, a self-supervised framework for novel view synthesis (NVS) in dynamic environments where both the camera and objects move. Dynamic content breaks the multi-v…
Next-Embedding Prediction Makes Strong Vision Learners
Sihan Xu, Ziqiao Ma, Wenhao Chai +5
Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training mode…
Semantic-Free Procedural 3D Shapes Are Surprisingly Good Teachers
Xuweiyi Chen, Zezhou Cheng
Self-supervised learning has emerged as a promising approach for acquiring transferable 3D representations from unlabeled 3D point clouds. Unlike 2D images, which are widely access…
Empowering Dynamic Urban Navigation with Stereo and Mid-Level Vision
Wentao Zhou, Xuweiyi Chen, Vignesh Rajagopal +3
The success of foundation models in language and vision motivated research in fully end-to-end robot navigation foundation models (NFMs). NFMs directly map monocular visual input t…
Open Vocabulary Monocular 3D Object Detection
Jin Yao, Hao Gu, Xuweiyi Chen +2
We propose and study open-vocabulary monocular 3D detection, a novel task that aims to detect objects of any categores in metric 3D space from a single RGB image. Existing 3D objec…