15 citations · 25 across the 13 of their papers we have counts for
18 papers
FreeLoc: Online Floorplan Localization via Diffusion-Aided Pose Refinement
Haocheng Peng, Boyang Zhou, Jiarui Hu +7
Floorplans provide compact and widely available geometric maps for indoor localization, but existing high-performing floorplan-based methods still convert them into dense scene-spe…
Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation
Zesong Yang, Weikai Chen, Liyuan Cui +10
Long-horizon camera-controlled video generation requires recovering previously observed content from an ever-growing visual history. Existing approaches either search historical co…
AutoPath: Learning Transferable Goal-Conditioned Stochastic Path Prior for Safe Navigation Without Human Demonstrations
Ziyang Zhang, Boyang Zhou, Zesong Yang +8
Real-time navigation in cluttered and dynamic environments requires collision-free and dynamically feasible motion under limited perception. However, feasible navigation behaviors…
MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing
Zesong Yang, Yuanhang Lei, Liyuan Cui +6
Recent advances integrate physically grounded Newtonian dynamics with neural rendering frameworks, narrowing the gap between photorealistic scene reconstruction and physics-based a…
NeuMesh++: Towards Versatile and Efficient Volumetric Editing with Disentangled Neural Mesh-based Implicit Field
Chong Bao, Yuan Li, Bangbang Yang +5
Recently neural implicit rendering techniques have evolved rapidly and demonstrated significant advantages in novel view synthesis and 3D scene reconstruction. However, existing ne…
GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidance
Jiale Shi, Jiarui Hu, Zesong Yang +3
We introduce GaussianZoom, a generative zoom-in 3D reconstruction system with an iterative progressive framework that combines geometry-consistent scene modeling and multi-scale se…
PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
Yuanhang Lei, Tao Cheng, Xingxuan Li +6
Achieving real-time physics-based animation that generalizes across diverse 3D shapes and discretizations remains a fundamental challenge. We introduce PhysSkin, a physics-informed…
DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics
Yuanhang Lei, Boming Zhao, Zesong Yang +10
Modeling wind-driven object dynamics from video observations is highly challenging due to the invisibility and spatio-temporal variability of wind, as well as the complex deformati…
Fuse3D: Generating 3D Assets Controlled by Multi-Image Fusion
Xuancheng Jin, Rengan Xie, Wenting Zheng +3
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 contro…
Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation
Yongzhen Hu, Yihui Yang, Haotong Lin +8
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 representat…
GaussianUpdate: Continual 3D Gaussian Splatting Update for Changing Environments
Lin Zeng, Boming Zhao, Jiarui Hu +4
Novel view synthesis with neural models has advanced rapidly in recent years, yet adapting these models to scene changes remains an open problem. Existing methods are either labor-…
InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes
Zesong Yang, Bangbang Yang, Wenqi Dong +5
Humans can naturally identify and mentally complete occluded objects in cluttered environments. However, imparting similar cognitive ability to robotics remains challenging even wi…
HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation
Wenqi Dong, Bangbang Yang, Zesong Yang +5
Scene-level 3D generation represents a critical frontier in multimedia and computer graphics, yet existing approaches either suffer from limited object categories or lack editing f…
CFSynthesis: Controllable and Free-view 3D Human Video Synthesis
Liyuan Cui, Xiaogang Xu, Wenqi Dong +3
Human video synthesis aims to create lifelike characters in various environments, with wide applications in VR, storytelling, and content creation. While 2D diffusion-based methods…
GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface Reconstruction
Zesong Yang, Ru Zhang, Jiale Shi +5
Neural surface representation has demonstrated remarkable success in the areas of novel view synthesis and 3D reconstruction. However, assessing the geometric quality of 3D reconst…
PC-Planner: Physics-Constrained Self-Supervised Learning for Robust Neural Motion Planning with Shape-Aware Distance Function
Xujie Shen, Haocheng Peng, Zesong Yang +4
Motion Planning (MP) is a critical challenge in robotics, especially pertinent with the burgeoning interest in embodied artificial intelligence. Traditional MP methods often strugg…
GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis
Boming Zhao, Yuan Li, Ziyu Sun +6
Forecasting future scenarios in dynamic environments is essential for intelligent decision-making and navigation, a challenge yet to be fully realized in computer vision and roboti…
Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning
Wenqi Dong, Bangbang Yang, Lin Ma +5
As humans, we aspire to create media content that is both freely willed and readily controlled. Thanks to the prominent development of generative techniques, we now can easily util…