8 papers
Unified Video Dense Prediction from Disjoint Data
Yihong Sun, Seoung Wug Oh, Jiahui Huang +2
Scene understanding requires simultaneous prediction about geometry, appearance, and semantics. However, existing task-specific annotations are fragmented across incompatible, doma…
DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
Tuan Duc Ngo, Jiahui Huang, Seoung Wug Oh +4
Estimating accurate, view-consistent geometry and camera poses from uncalibrated multi-view/video inputs remains challenging - especially at high spatial resolutions and over long…
Generative Video Motion Editing with 3D Point Tracks
Yao-Chih Lee, Zhoutong Zhang, Jiahui Huang +5
Camera and object motions are central to a video's narrative. However, precisely editing these captured motions remains a significant challenge, especially under complex object mov…
AnthroTAP: Learning Point Tracking with Real-World Motion
Inès Hyeonsu Kim, Seokju Cho, Jahyeok Koo +5
Point tracking models often struggle to generalize to real-world videos because large-scale training data is predominantly synthetic$\unicode{x2014}$the only source currently feasi…
FRAME: Pre-Training Video Feature Representations via Anticipation and Memory
Sethuraman TV, Savya Khosla, Vignesh Srinivasakumar +5
Dense video prediction tasks, such as object tracking and semantic segmentation, require video encoders that generate temporally consistent, spatially dense features for every fram…
Seurat: From Moving Points to Depth
Seokju Cho, Jiahui Huang, Seungryong Kim +1
Accurate depth estimation from monocular videos remains challenging due to ambiguities inherent in single-view geometry, as crucial depth cues like stereopsis are absent. However,…
Exploring Temporally-Aware Features for Point Tracking
Inès Hyeonsu Kim, Seokju Cho, Jiahui Huang +3
Point tracking in videos is a fundamental task with applications in robotics, video editing, and more. While many vision tasks benefit from pre-trained feature backbones to improve…
Local All-Pair Correspondence for Point Tracking
Seokju Cho, Jiahui Huang, Jisu Nam +3
We introduce LocoTrack, a highly accurate and efficient model designed for the task of tracking any point (TAP) across video sequences. Previous approaches in this task often rely…