Hujun Bao

A fusion flexible implementation rasterization engine for neural rendering on AI accelerators

Xinkai Yan, Kaiwen Ji, Suiliang Mai, Yuchi Huo et autres

cn (code pays fourni par la source)

A Neural Frame Streaming Framework with a Simultaneous Prior for End-cloud Collaborative Rendering

Hangming Fan, Yazhen Yuan, Yongyu Ding, Yuwen Chen et autres

Cloud rendering has gained much attention recently since it alleviates the client’s computing cost by distributing most of the rendering tasks on the cloud, and the rendered frames are compressed and streamed to a client device for display. However, the accessibility of …

cn (code pays fourni par la source)

Component Modes Synthesis Method with Multiple Partitions for Large-scale Eigenvalue Problem

Chongyao Zhao, Junzhou Yin, Hujun Bao, Jin Huang

For large-scale modal analysis problems, Component Mode Synthesis (CMS) methods are very attractive, as they reduce the global problem into smaller subproblems on substructures. However, the substructure bases do not span the desired solution space efficiently, thus the error decreases slowly as …

cn (code pays fourni par la source)

Efficient Object Reconstruction with Differentiable Area Light Shading

Yaoan Gao, Jiamin Xu, James Tompkin, Qi Wang et autres

In 3D object reconstruction from photographs, estimating material properties is challenging. We propose an inverse rendering method that uses active area lighting: as this provides a wider range of lighting angles per photo than point lighting, material reconstruction can be more accurate …

cn, us (code pays fourni par la source)

Fuse3D: Generating 3D Assets Controlled by Multi-Image Fusion

Xuancheng Jin, Rengan Xie, Wenting Zheng, Rui Wang et autres

Recently, generating 3D assets with the control of condition images has achieved impressive quality. However, existing 3D generation methods are limited to handling a single control objective and lack the ability to utilize multiple images to independently control different regions of a …

cn (code pays fourni par la source)

NeLiF: Neural Lighting Function Generation for Real-Time Indoor Rendering

Hongtao Sheng, Yuchi Huo, Chuankun Zheng, Guangzhi Han et autres

Recent advances in neural rendering have mainly focused on modeling radiance fields with neural representations, often overlooking the underlying mechanisms for producing various lighting effects, and consequently leading to the limited adaptability to dynamic scenes. Lighting effects, such as highlights, shadows, and …

cn, hk (code pays fourni par la source)

Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation

Yongzhen Hu, Yihui Yang, Haotong Lin, Junting Dong et autres

This paper addresses the problem of decomposed 4D scene reconstruction from multi-view videos. Recent methods achieve this by lifting video segmentation results to a 4D representation through differentiable rendering techniques. Therefore, they heavily rely on the quality of video segmentation maps, which …

cn (code pays fourni par la source)

Variational Mesh Offsetting by Smoothed Winding Number

Shuang Wu, Hujun Bao

Surface mesh offsetting is a fundamental operation in various applications (e.g., shape modeling). Implicit methods that contour a volumetric distance field are robust at handling intersection defects, but it is challenging to apply shape control (e.g., preserving sharp features in the input …

cn (code pays fourni par la source)

Street Gaussians: Modeling Dynamic Urban Scenes With Gaussian Primitives

Sida Peng, Yunzhi Yan, Haotong Lin, Chenxu Zhou et autres

This paper aims to tackle the problem of modeling dynamic urban streets for autonomous driving scenes. Recent methods extend NeRF by incorporating tracked vehicle poses to animate vehicles, enabling photo-realistic view synthesis of dynamic urban street scenes. However, significant limitations are their …

cn (code pays fourni par la source)

Bidirectional Temporal-Aware Modeling with Multi-Scale Mixture-of-Experts for Multivariate Time Series Forecasting

Boming Zhao, Haocheng Peng, Hujun Bao, Jiashu Zhao et autres

Recent advances in deep learning have significantly boosted performance in multivariate time series forecasting (MTSF). While many existing approaches focus on capturing inter-variable (a.k.a. channel-wise) correlations to improve prediction accuracy, the temporal dimension, particularly its rich structural and contextual information, remains underexplored. …

cn, ca (code pays fourni par la source)

HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation

Wenqi Dong, Bangbang Yang, Zesong Yang, Yuan Li et autres

Scene-level 3D generation represents a critical frontier in multimedia and computer graphics. While existing approaches have achieved encouraging progress, they still face challenges such as constrained object diversity and limited support for interactive editing. In this paper, we present HiScene, a novel …

cn (code pays fourni par la source)

BlinkTrack: Feature Tracking Over 80 FPS via Events and Images

Yichen Shen, Yijin Li, Shuo Chen, Guanglin Li et autres

Event cameras, known for their high temporal resolution and ability to capture asynchronous changes, have gained significant attention for their potential in feature tracking, especially in challenging conditions. However, event cameras lack the fine-grained texture information that conventional cameras provide, leading to …

cn, us (code pays fourni par la source)