MrNeRF (@janusch_patas)
2024-10-18 | โค๏ธ 177 | ๐ 23
DepthSplat: Connecting Gaussian Splatting and Depth
Abstract (excerpt): We present DepthSplat to connect Gaussian splatting and depth estimation and study their interactions.
More specifically, we first contribute a robust multi-view depth model by leveraging pre-trained monocular depth features, leading to high-quality feed-forward 3D Gaussian splatting reconstructions.
We also show that Gaussian splatting can serve as an unsupervised pretraining objective for learning powerful depth models from large-scale unlabelled datasets.
We validate the synergy between Gaussian splatting and depth estimation through extensive ablation and cross-task transfer experiments.
Our DepthSplat achieves state-of-the-art performance on ScanNet, RealEstate10K and DL3DV datasets in terms of both depth estimation and novel view synthesis, demonstrating the mutual benefits of connecting both tasks.
๋ฏธ๋์ด
