20 results for “video processing”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Jie Deng, Heyang Wang, Changxin Wang, Junkai Shen +5 more
This paper introduces IR275K, a curated benchmark for multi-frame super-resolution in infrared remote sensing, and evaluates CGMamba, a lightweight state-space model, achieving state-of-the-art perfor…
Noam Rotstein, Yoad Tewel, Chen Tessler, Haggai Maron +4 more
A model that co-generates video and 3D motion for any supplied rig, along with a camera that registers this motion to the scene.
The paper presents OC-GS, an object-centric Gaussian splatting method that refines image angles while maintaining a shared camera, rotation axis, and pivot for turntable reconstruction.
The paper presents a new method for precise control over spatial transformations in image editing using 3D boxes as structured specifications.
Yuyang Zhao, Yicheng Pan, Qiyuan He, Jincheng Yu +5 more
SANA-Streaming introduces a novel, efficient framework that enables real-time, high-resolution streaming video-to-video editing by combining a hybrid diffusion transformer with specialized training an…
Weijie Lyu, Tiancheng Shen, Jason Li, Yujing Wang +4 more
This paper proposes a post-hoc video-to-video model called Video Geometry Corrector (VGC) to improve geometric consistency in generated videos.
This paper analyzes the proprietary file system of Honeywell video surveillance devices, demonstrating that video data can be successfully recovered even after deletion using three different methods:…
This paper proposes using color statistics, specifically through novel color transformations, to detect AI-generated synthetic images by exploiting the color-imitation weaknesses of current generative…
First implementation of a 3D Gaussian renderer on an Intelligence Processing Unit (IPU) with 1,472 independent tiles using only on-chip SRAM.
The paper describes how to compute singular value soft-thresholding using matrix polar decomposition for faster GPU processing.
A hardwired distributed processing unit (HDPU) is designed to make neural decisions at the sensor, reducing inference on the host.