2 citations · 2 across the 12 of their papers we have counts for
14 papers
GS-PI: An Optimization-Decoupled Appearance Decomposition Approach for Generating PBR Gaussian Assets
Jieting Xu, Rengan Xie, Zijian Huang +3
Gaussian Splatting (GS) excels at novel-view synthesis but encodes baked-in radiance, tightly entangling illumination with geometry and preventing seamless integration into physica…
ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions
Xintong Fang, Zhiyuan Fang, Rengan Xie +6
Recent progress in image and 3D scene generation has enabled increasingly realistic static environments, yet most methods remain confined to such static configurations. Generating…
ES3D: Embedding Semantics into 3D Space for Component-Aware Editing
Xuancheng Jin, Rengan Xie, Jiayuan Lu +5
Existing 3D editing methods have made notable progress in controllability, yet they remain limited in several important ways. Most approaches rely on text-driven editing, which str…
HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generation
Bin Zang, Wenting Zheng, Xiaoliang Luo +8
Recently, a line of works can generate impressive 3D objects from a single image, but they are limited by restricted representation resolution, making them unsuitable for 3D scene…
Texture++: Elevating 3D Asset Texture Resolution with a Region-Aware Diffusion Model
Shuaiwei Wang, Shi Li, Jieting Xu +4
Numerous 3D assets are discarded due to low texture resolution, while current super-resolution models ignore texture maps and focus on natural images. An efficient and generalizabl…
GeRM: A Generative Rendering Model From Physically Realistic to Photorealistic
Jiayuan Lu, Rengan Xie, Xuancheng Jin +5
While physically-based rendering (PBR) simulates light transport that guarantees physical realism, achieving true photorealistic rendering (PRR) demands prohibitive time and labor,…
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…
LiDAR-GS++:Improving LiDAR Gaussian Reconstruction via Diffusion Priors
Qifeng Chen, Jiarun Liu, Rengan Xie +5
Recent GS-based rendering has made significant progress for LiDAR, surpassing Neural Radiance Fields (NeRF) in both quality and speed. However, these methods exhibit artifacts in e…
LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting
Qifeng Chen, Sheng Yang, Sicong Du +4
We present LiDAR-GS, a Gaussian Splatting (GS) method for real-time, high-fidelity re-simulation of LiDAR scans in public urban road scenes. Recent GS methods proposed for cameras…
HR Human: Modeling Human Avatars with Triangular Mesh and High-Resolution Textures from Videos
Qifeng Chen, Rengan Xie, Kai Huang +4
Recently, implicit neural representation has been widely used to generate animatable human avatars. However, the materials and geometry of those representations are coupled in the…
LDM: Large Tensorial SDF Model for Textured Mesh Generation
Rengan Xie, Wenting Zheng, Kai Huang +5
Previous efforts have managed to generate production-ready 3D assets from text or images. However, these methods primarily employ NeRF or 3D Gaussian representations, which are not…
2L3: Lifting Imperfect Generated 2D Images into Accurate 3D
Yizheng Chen, Rengan Xie, Qi Ye +5
Reconstructing 3D objects from a single image is an intriguing but challenging problem. One promising solution is to utilize multi-view (MV) 3D reconstruction to fuse generated MV…
In-Hand 3D Object Reconstruction from a Monocular RGB Video
Shijian Jiang, Qi Ye, Rengan Xie +4
Our work aims to reconstruct a 3D object that is held and rotated by a hand in front of a static RGB camera. Previous methods that use implicit neural representations to recover th…
Holistic Inverse Rendering of Complex Facade via Aerial 3D Scanning
Zixuan Xie, Rengan Xie, Rong Li +8
In this work, we use multi-view aerial images to reconstruct the geometry, lighting, and material of facades using neural signed distance fields (SDFs). Without the requirement of…