9 papers
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…
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…
4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time
Ziqiao Ma, Xuweiyi Chen, Shoubin Yu +10
Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at some times to any view at any time? We provide an affirmative…
SAB3R: Semantic-Augmented Backbone in 3D Reconstruction
Xuweiyi Chen, Tian Xia, Sihan Xu +3
We introduce a new task, Map and Locate, which unifies the traditionally distinct objectives of open-vocabulary segmentation - detecting and segmenting object instances based on na…
Frame In-N-Out: Unbounded Controllable Image-to-Video Generation
Boyang Wang, Xuweiyi Chen, Matheus Gadelha +1
Controllability, temporal coherence, and detail synthesis remain the most critical challenges in video generation. In this paper, we focus on a commonly used yet underexplored cine…