7 papers · 1 filter
Cambrian-P: Pose-Grounded Video Understanding
Jihan Yang, Zifan Zhao, Xichen Pan +6
Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video frames. Yet this signal is large…
LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
Junyi Zhang, Charles Herrmann, Junhwa Hur +5
Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or lim…
Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment
Youming Deng, Songyou Peng, Junyi Zhang +5
Novel View Synthesis (NVS) has traditionally relied on models with explicit 3D inductive biases combined with known camera parameters from Structure-from-Motion (SfM) beforehand. R…
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
Junyi Zhang, Charles Herrmann, Junhwa Hur +5
Estimating geometry from dynamic scenes, where objects move and deform over time, remains a core challenge in computer vision. Current approaches often rely on multi-stage pipeline…
St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
Haiwen Feng, Junyi Zhang, Qianqian Wang +5
Dynamic 3D reconstruction and point tracking in videos are typically treated as separate tasks, despite their deep connection. We propose St4RTrack, a feed-forward framework that s…
From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding
Yong-Lu Li, Xiaoqian Wu, Xinpeng Liu +8
Action understanding has attracted long-term attention. It can be formed as the mapping from the physical space to the semantic space. Typically, researchers built datasets accordi…