4 papers
RoSplat: Robust Feed-Forward Pixel-wise Gaussian Splatting for Varying Input Views and High-Resolution Rendering
Hoang Chuong Nguyen, Renjie Wu, Jose M. Alvarez +1
Generalizable 3D Gaussian Splatting has recently emerged as an efficient approach for novel-view synthesis, enabling feed-forward synthesis from only a few input views. However, ex…
IBGS: Image-Based Gaussian Splatting
Hoang Chuong Nguyen, Wei Mao, Jose M. Alvarez +1
3D Gaussian Splatting (3DGS) has recently emerged as a fast, high-quality method for novel view synthesis (NVS). However, its use of low-degree spherical harmonics limits its abili…
Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video
Hoang Chuong Nguyen, Wei Mao, Jose M. Alvarez +1
Neural Radiance Fields (NeRF) has demonstrated its superior capability to represent 3D geometry but require accurately precomputed camera poses during training. To mitigate this re…
Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation
Hoang Chuong Nguyen, Tianyu Wang, Jose M. Alvarez +1
This paper focuses on self-supervised monocular depth estimation in dynamic scenes trained on monocular videos. Existing methods jointly estimate pixel-wise depth and motion, relyi…