|
|
Graph2Scene: Versatile 3D Indoor Scene Generation with Interaction-aware Scene Graph
Minglin Chen,
Rongkun Yang,
Qibin Hu,
Kaiwen Xue,
Shunbo Zhou,
Yulan Guo
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025
Graph2Scene learns to generate 3D indoor scenes with interaction-aware scene graphs.
|
|
|
DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering
Yexing Xu*,
Longguang Wang*,
Minglin Chen,
Sheng Ao,
Li Li,
Yulan Guo
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
Project page
|
arXiv
|
Code
DropoutGS explores the use of dropping out Gaussians for better sparse-view rendering.
|
|
|
Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors
Minglin Chen,
Longguang Wang,
Sheng Ao,
Ye Zhang,
Kai Xu,
Yulan Guo
arXiv, 2025
arXiv
Layout2Scene generates 3D realistic indoor scenes from 3D layouts.
|
|
|
WSSIC-Net: Weakly-Supervised Semantic Instance Completion of 3D Point Cloud Scenes
Zhiheng Fu,
Yulan Guo,
Minglin Chen,
Qingyong Hu,
Hamid Laga,
Farid Boussaid,
Mohammed Bennamoun
IEEE Transactions on Image Processing (IEEE TIP), 2025
Paper
WSSIC-Net is a weakly-supervised semantic instance completion model for 3D point cloud scenes.
|
|
|
Tangram-Splatting: Optimizing 3D Gaussian Splatting Through Tangram-inspired Shape Priors
Yi Wang,
Ningze Zhong,
Minglin Chen,
Longguang Wang,
Yulan Guo
ACM International Conference on Multimedia (ACM'MM), 2024
Paper
Tangram-Splatting explore different shape Gaussian for efficient novel view synthesis.
|
|
|
Distractor-free Novel View Synthesis via Exploiting Memorization Effect in Optimization
Yukun Wang,
Kunhong Li,
Minglin Chen,
Longguang Wang,
Shunbo Zhou,
Kaiwen Xue,
Yulan Guo
The European Conference on Computer Vision (ECCV), 2024
Paper
|
Code
The work explores the memorization effect in optimization for distractor-free novel view synthesis.
|
|
|
Sketch2NeRF: Multi-view Sketch-guided Text-to-3D Generation
Minglin Chen,
Longguang Wang,
Weihao Yuan,
Yukun Wang,
Zhe Sheng,
Yisheng He,
Zilong Dong,
Liefeng Bo,
Yulan Guo
arXiv, 2024
arXiv
Sketch2NeRF is a sketch-guided text-to-3D generative model that produces high-fidelity 3D objects resembling multi-view sketches.
|
|
|
Learning Spherical Radiance Field for Efficient 360° Unbounded Novel View Synthesis
Minglin Chen,
Longguang Wang,
Yinjie Lei,
Zilong Dong,
Yulan Guo
IEEE Transactions on Image Processing (IEEE TIP), 2024
Project page
|
Code
We present the Spherical Radiance Field to achieve efficient novel view synthesis on 360° unbounded scene.
|
