Search Results for author: Jiaben Chen

Found 9 papers, 2 papers with code

SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation

no code implementations31 Aug 2023 Jiaben Chen, Huaizu Jiang

We re-train several state-of-the-art methods on our benchmark, and the results show a decrease in their accuracy compared to other datasets.

Panoptic Segmentation Video Frame Interpolation

Deceptive-NeRF: Enhancing NeRF Reconstruction using Pseudo-Observations from Diffusion Models

no code implementations24 May 2023 Xinhang Liu, Jiaben Chen, Shiu-hong Kao, Yu-Wing Tai, Chi-Keung Tang

We introduce Deceptive-NeRF, a novel methodology for few-shot NeRF reconstruction, which leverages diffusion models to synthesize plausible pseudo-observations to improve the reconstruction.

iQuery: Instruments as Queries for Audio-Visual Sound Separation

1 code implementation CVPR 2023 Jiaben Chen, Renrui Zhang, Dongze Lian, Jiaqi Yang, Ziyao Zeng, Jianbo Shi

To generalize to a new instrument or event class, drawing inspiration from the text-prompt design, we insert an additional query as an audio prompt while freezing the attention mechanism.

Disentanglement

Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation

no code implementations2 Oct 2022 Xinhang Liu, Jiaben Chen, Huai Yu, Yu-Wing Tai, Chi-Keung Tang

The core of our method is a novel propagation strategy for individual objects' radiance fields with a bidirectional photometric loss, enabling an unsupervised partitioning of a scene into salient or meaningful regions corresponding to different object instances.

3D Object Editing Object +2

VECtor: A Versatile Event-Centric Benchmark for Multi-Sensor SLAM

no code implementations4 Jul 2022 Ling Gao, Yuxuan Liang, Jiaqi Yang, Shaoxun Wu, Chenyu Wang, Jiaben Chen, Laurent Kneip

Event cameras have recently gained in popularity as they hold strong potential to complement regular cameras in situations of high dynamics or challenging illumination.

Simultaneous Localization and Mapping

DEVO: Depth-Event Camera Visual Odometry in Challenging Conditions

no code implementations5 Feb 2022 Yi-Fan Zuo, Jiaqi Yang, Jiaben Chen, Xia Wang, Yifu Wang, Laurent Kneip

We present a novel real-time visual odometry framework for a stereo setup of a depth and high-resolution event camera.

Computational Efficiency Visual Odometry

Cannot find the paper you are looking for? You can Submit a new open access paper.