6 papers
LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs
Jihwan Kim, Nikhil Parthasarathy, Danfeng Qin +5
The fundamental challenge in scaling Video Large Language Models (Video LLMs) to long-form video lies in managing the explosion of visual-token context length. Existing strategies…
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
Jisu Nam, Jahyeok Koo, Soowon Son +4
Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motio…
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…
UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images
Junhwa Hur, Charles Herrmann, Songyou Peng +4
Dense 4D reconstruction from unposed images remains a critical challenge, with current methods relying on slow test-time optimization or fragmented, task-specific feedforward model…
Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking
Soowon Son, Honggyu An, Jisu Nam +7
Despite achieving strong results on standard benchmarks, current point tracking methods rely on feature backbones that are rarely designed with the temporal coherence needed for ro…
Emergent Temporal Correspondences from Video Diffusion Transformers
Jisu Nam, Soowon Son, Dahyun Chung +4
Recent advancements in video diffusion models based on Diffusion Transformers (DiTs) have achieved remarkable success in generating temporally coherent videos. Yet, a fundamental q…