5 papers
Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation
Gongshu Wang, Zhirui Wang, Kan Yang
Monocular depth estimation (MDE) is a fundamental yet inherently ill-posed task. Recent vision foundation models (VFMs), particularly DINO-based transformers, have significantly im…
DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures
Xu Wang, Zhiru Wang, Shiyun Xie +2
While 3D Gaussian Splatting (3DGS) achieves real-time photorealistic rendering, its performance degrades significantly when training images contain transient objects that violate m…
WEDepth: Efficient Adaptation of World Knowledge for Monocular Depth Estimation
Gongshu Wang, Zhirui Wang, Kan Yang
Monocular depth estimation (MDE) has widely applicable but remains highly challenging due to the inherently ill-posed nature of reconstructing 3D scenes from single 2D images. Mode…
SuperGS: Consistent and Detailed 3D Super-Resolution Scene Reconstruction via Gaussian Splatting
Shiyun Xie, Zhiru Wang, Yinghao Zhu +3
Recently, 3D Gaussian Splatting (3DGS) has excelled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality. However, it encounters challenges…
SuperGS: Super-Resolution 3D Gaussian Splatting Enhanced by Variational Residual Features and Uncertainty-Augmented Learning
Shiyun Xie, Zhiru Wang, Xu Wang +3
Recently, 3D Gaussian Splatting (3DGS) has exceled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality. However, it faces challenges for hi…