Fusang Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fusang Wang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Arnaud Louys
Ark Lab Moussab Bennehar Shanghai Jiao Tong University Huawei Noah's Ark Lab Huawei Noah's Ark Lab Huawei Noah's Ark Lab Huawei Noah's Ark Lab Huawei Noah's Ark Lab
1 shared publication - Dzmitry Tsishkou
Noah’s Ark, Huawei Paris Research Center
1 shared publication - Luis Roldão
Noah’s Ark, Huawei Paris Research Center
1 shared publication - Moussab Bennehar
Noah’s Ark, Huawei Paris Research Center
1 shared publication - Nathan Piasco
Noah’s Ark, Huawei Paris Research Center
1 shared publication
Latest Publications
- Open Access
PlaNeRF: SVD Unsupervised 3D Plane Regularization for NeRF Large-Scale Scene Reconstruction
Neural Radiance Fields (NeRF) enable 3D scene reconstruction from 2D images and camera poses for Novel View Synthesis (NVS). Although NeRF can produce photorealistic results, it often suffers from overfitting to training views, leading to poor geometry reconstruction, especially in low-texture areas. This limitation restricts many important applications which require accurate geometry, such as extrapolated NVS, HD mapping and scene editing. To address this limitation, we propose a new method to improve NeRF's 3D structure using only RGB images and semantic maps. Our approach introduces a novel plane regularization based on Singular Value Decomposition (SVD), that does not rely on any geometric prior. In addition, we leverage the Structural Similarity Index Measure (SSIM) in our loss design to properly initialize the volumetric representation of NeRF. Quantitative and qualitative results show that our method outperforms popular regularization approaches in accurate geometry reconstruction for large-scale outdoor scenes and achieves SoTA rendering quality on the KITTI-360 NVS benchmark.
Open AccessPlaNeRF: SVD Unsupervised 3D Plane Regularization for NeRF Large-Scale Scene Reconstruction
Neural Radiance Fields (NeRF) enable 3D scene reconstruction from 2D images and camera poses for Novel View Synthesis (NVS). Although NeRF can produce photorealistic results, it often suffers from overfitting to training views, leading to poor geometry reconstruction, especially in low-texture areas. This limitation restricts many important applications which require accurate geometry, such as extrapolated NVS, HD mapping and scene editing. To address this limitation, we propose a new method to improve NeRF's 3D structure using only RGB images and semantic maps. Our approach introduces a novel plane regularization based on Singular Value Decomposition (SVD), that does not rely on any geometric prior. In addition, we leverage the Structural Similarity Index Measure (SSIM) in our loss design to properly initialize the volumetric representation of NeRF. Quantitative and qualitative results show that our method outperforms popular regularization approaches in accurate geometry reconstruction for large-scale outdoor scenes and achieves SoTA rendering quality on the KITTI-360 NVS benchmark.