4 citations · 8 across the 13 of their papers we have counts for
14 papers
PUGS: Physics-Guided Uncertainty Modeling for Underwater Dynamic 3D Gaussian Splatting
Tingjun Li, Yuxi Wang, Guoqiang Zhong +1
Dynamic 3D Gaussian Splatting (3DGS) provides an efficient framework for dynamic scene reconstruction. Most existing approaches model scene dynamics with deterministic deformation…
Ocean4D: Generative Underwater 4D Reconstruction via Medium-Aware Video Diffusion
Yuqiang Huang, Yuxi Wang, Junyu Dong +1
Underwater 4D reconstruction remains challenging due to the coupling between degraded light transport in participating media and dynamic water variations. Most existing Methods are…
HLG: Comprehensive 3D Room Construction via Hierarchical Layout Generation
Xiping Wang, Yuxi Wang, Mengqi Zhou +2
Realistic 3D indoor scene generation is crucial for virtual reality, interior design, embodied intelligence, and scene understanding. While existing methods have made progress in c…
RoomCraft: Controllable and Complete 3D Indoor Scene Generation
Mengqi Zhou, Xipeng Wang, Yuxi Wang +1
Generating realistic 3D indoor scenes from user inputs remains a challenging problem in computer vision and graphics, requiring careful balance of geometric consistency, spatial re…
EmoDiffusion: Enhancing Emotional 3D Facial Animation with Latent Diffusion Models
Yixuan Zhang, Qing Chang, Yuxi Wang +3
Speech-driven 3D facial animation seeks to produce lifelike facial expressions that are synchronized with the speech content and its emotional nuances, finding applications in vari…
OOD-HOI: Text-Driven 3D Whole-Body Human-Object Interactions Generation Beyond Training Domains
Yixuan Zhang, Hui Yang, Chuanchen Luo +3
Generating realistic 3D human-object interactions (HOIs) from text descriptions is a active research topic with potential applications in virtual and augmented reality, robotics, a…
Enhancing Sound Source Localization via False Negative Elimination
Zengjie Song, Jiangshe Zhang, Yuxi Wang +2
Sound source localization aims to localize objects emitting the sound in visual scenes. Recent works obtaining impressive results typically rely on contrastive learning. However, t…
CityX: Controllable Procedural Content Generation for Unbounded 3D Cities
Shougao Zhang, Mengqi Zhou, Yuxi Wang +5
Urban areas, as the primary human habitat in modern civilization, accommodate a broad spectrum of social activities. With the surge of embodied intelligence, recent years have witn…
MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assets
Zeyu Li, Ruitong Gan, Chuanchen Luo +7
Driven by powerful image diffusion models, recent research has achieved the automatic creation of 3D objects from textual or visual guidance. By performing score distillation sampl…
StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework
Yiheng Huang, Hui Yang, Chuanchen Luo +5
Thanks to the powerful generative capacity of diffusion models, recent years have witnessed rapid progress in human motion generation. Existing diffusion-based methods employ dispa…
MemoNav: Working Memory Model for Visual Navigation
Hongxin Li, Zeyu Wang, Xu Yang +3
Image-goal navigation is a challenging task that requires an agent to navigate to a goal indicated by an image in unfamiliar environments. Existing methods utilizing diverse scene…
SceneX: Procedural Controllable Large-scale Scene Generation
Mengqi Zhou, Yuxi Wang, Jun Hou +5
Developing comprehensive explicit world models is crucial for understanding and simulating real-world scenarios. Recently, Procedural Controllable Generation (PCG) has gained signi…
FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes
Genghao Zhang, Yuxi Wang, Chuanchen Luo +4
Indoor scene generation has attracted significant attention recently as it is crucial for applications of gaming, virtual reality, and interior design. Current indoor scene generat…
Bootstrap Masked Visual Modeling via Hard Patches Mining
Haochen Wang, Junsong Fan, Yuxi Wang +4
Masked visual modeling has attracted much attention due to its promising potential in learning generalizable representations. Typical approaches urge models to predict specific con…