XYScanNet: An Interpretable State Space Model for Perceptual Image Deblurring

no code implementations • 13 Dec 2024 • Hanzhou Liu, Chengkai Liu, Jiacong Xu, Peng Jiang, Mi Lu

Deep state-space models (SSMs), like recent Mamba architectures, are emerging as a promising alternative to CNN and Transformer networks.

Deblurring Image Deblurring +2

Reference-based Controllable Scene Stylization with Gaussian Splatting

no code implementations • 9 Jul 2024 • Yiqun Mei, Jiacong Xu, Vishal M. Patel

Simply optimizing the appearance as prior methods do is often insufficient for modeling continuous textures in the given reference image.

Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections

no code implementations • 14 Jun 2024 • Jiacong Xu, Yiqun Mei, Vishal M. Patel

Unlike previous methods that model reference features in image space, Wild-GS explicitly aligns the pixel appearance features to the corresponding local Gaussians by sampling the triplane extracted from the reference image.

Novel View Synthesis

Leveraging Thermal Modality to Enhance Reconstruction in Low-Light Conditions

1 code implementation • 21 Mar 2024 • Jiacong Xu, Mingqian Liao, K Ram Prabhakar, Vishal M. Patel

To address these issues, we present Thermal-NeRF, which takes thermal and visible raw images as inputs, considering the thermal camera is robust to the illumination variation and raw images preserve any possible clues in the dark, to accomplish visible and thermal view synthesis simultaneously.

3D Reconstruction Novel View Synthesis

Communication-Efficient Design of Learning System for Energy Demand Forecasting of Electrical Vehicles

no code implementations • 4 Sep 2023 • Jiacong Xu, Riley Kilfoyle, Zixiang Xiong, Ligang Lu

In this paper, we propose a communication-efficient time series forecasting model combining the most recent advancements in transformer architectures implemented across a geographically dispersed series of EV charging stations and an efficient variant of federated learning (FL) to enable distributed training.

Demand Forecasting Federated Learning +3

Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape

no code implementations • ICCV 2023 • Jiacong Xu, Yi Zhang, Jiawei Peng, Wufei Ma, Artur Jesslen, Pengliang Ji, Qixin Hu, Jiehua Zhang, Qihao Liu, Jiahao Wang, Wei Ji, Chen Wang, Xiaoding Yuan, Prakhar Kaushik, Guofeng Zhang, Jie Liu, Yushan Xie, Yawen Cui, Alan Yuille, Adam Kortylewski

Animal3D consists of 3379 images collected from 40 mammal species, high-quality annotations of 26 keypoints, and importantly the pose and shape parameters of the SMAL model.

Animal Pose Estimation

PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers

6 code implementations • CVPR 2023 • Jiacong Xu, Zixiang Xiong, Shankar P. Bhattacharyya

To alleviate this problem, we propose a novel three-branch network architecture: PIDNet, which contains three branches to parse detailed, context and boundary information, respectively, and employs boundary attention to guide the fusion of detailed and context branches.

Real-Time Semantic Segmentation