231 citations · 236 across the 12 of their papers we have counts for
13 papers
Exo2EgoHOI: Hand-Object-Interaction Aware Exocentric-to-Egocentric Video Generation
Hongjia Zhai, Xiyu Zhang, Haoran Zhang +5
Egocentric videos of human manipulation provide valuable visual experience for embodied intelligence, yet collecting such data at scale is costly. Exocentric-to-egocentric video ge…
WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images
Xiyu Zhang, Jingyu Zhuang, Hongjia Zhai +4
While feedforward 3D reconstruction excels at efficient novel view synthesis, it typically falters when faced with scenes under varying illumination. To this end, we introduce Wild…
INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling
InSpatio Team, Donghui Shen, Guofeng Zhang +20
Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle wit…
OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting
Hongjia Zhai, Qi Zhang, Xiaokun Pan +5
Open-vocabulary scene understanding with online panoptic mapping is essential for embodied applications to perceive and interact with environments. However, existing methods are pr…
EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly
Xiaokun Pan, Zhenzhe Li, Zhichao Ye +2
Real-time 3D reconstruction is a fundamental task in computer graphics. Recently, differentiable-rendering-based SLAM system has demonstrated significant potential, enabling photor…
AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians
Xiyu Zhang, Chong Bao, Yipeng Chen +5
3D reconstruction of indoor and urban environments is a prominent research topic with various downstream applications. However, existing geometric priors for addressing low-texture…
PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding
Hongjia Zhai, Hai Li, Zhenzhe Li +3
Recently, 3D Gaussian Splatting (3DGS) has shown encouraging performance for open vocabulary scene understanding tasks. However, previous methods cannot distinguish 3D instance-lev…
NeuraLoc: Visual Localization in Neural Implicit Map with Dual Complementary Features
Hongjia Zhai, Boming Zhao, Hai Li +5
Recently, neural radiance fields (NeRF) have gained significant attention in the field of visual localization. However, existing NeRF-based approaches either lack geometric constra…
SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality
Hongjia Zhai, Xiyu Zhang, Boming Zhao +5
Visual localization plays an important role in the applications of Augmented Reality (AR), which enable AR devices to obtain their 6-DoF pose in the pre-build map in order to rende…
NIS-SLAM: Neural Implicit Semantic RGB-D SLAM for 3D Consistent Scene Understanding
Hongjia Zhai, Gan Huang, Qirui Hu +3
In recent years, the paradigm of neural implicit representations has gained substantial attention in the field of Simultaneous Localization and Mapping (SLAM). However, a notable g…
Vox-Fusion++: Voxel-based Neural Implicit Dense Tracking and Mapping with Multi-maps
Hongjia Zhai, Hai Li, Xingrui Yang +4
In this paper, we introduce Vox-Fusion++, a multi-maps-based robust dense tracking and mapping system that seamlessly fuses neural implicit representations with traditional volumet…
Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation
Xingrui Yang, Hai Li, Hongjia Zhai +3
In this work, we present a dense tracking and mapping system named Vox-Fusion, which seamlessly fuses neural implicit representations with traditional volumetric fusion methods. Ou…
Vox-Surf: Voxel-based Implicit Surface Representation
Hai Li, Xingrui Yang, Hongjia Zhai +3
Virtual content creation and interaction play an important role in modern 3D applications such as AR and VR. Recovering detailed 3D models from real scenes can significantly expand…