activity
20242026
collaborators

5 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2024

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…