5 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…
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…
EA3D: Online Open-World 3D Object Extraction from Streaming Videos
Xiaoyu Zhou, Jingqi Wang, Yuang Jia +3
Current 3D scene understanding methods are limited by offline-collected multi-view data or pre-constructed 3D geometry. In this paper, we present ExtractAnything3D (EA3D), a unifie…
DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes
Yajiao Xiong, Xiaoyu Zhou, Yongtao Wan +2
We present DrivingGaussian++, an efficient and effective framework for realistic reconstructing and controllable editing of surrounding dynamic autonomous driving scenes. DrivingGa…
HoliSDiP: Image Super-Resolution via Holistic Semantics and Diffusion Prior
Li-Yuan Tsao, Hao-Wei Chen, Hao-Wei Chung +4
Text-to-image diffusion models have emerged as powerful priors for real-world image super-resolution (Real-ISR). However, existing methods may produce unintended results due to noi…