SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
It addresses the scalability issue in 3D reconstruction for computer vision by enabling the use of larger, more diverse datasets without pose supervision.
The paper tackles the problem of 3D Gaussian splatting from sparse multi-view images without ground-truth poses, achieving state-of-the-art performance in novel view synthesis under challenging conditions like extreme viewpoint changes and limited image overlap.
We introduce SPFSplatV2, an efficient feed-forward framework for 3D Gaussian splatting from sparse multi-view images, requiring no ground-truth poses during training and inference. It employs a shared feature extraction backbone, enabling simultaneous prediction of 3D Gaussian primitives and camera poses in a canonical space from unposed inputs. A masked attention mechanism is introduced to efficiently estimate target poses during training, while a reprojection loss enforces pixel-aligned Gaussian primitives, providing stronger geometric constraints. We further demonstrate the compatibility of our training framework with different reconstruction architectures, resulting in two model variants. Remarkably, despite the absence of pose supervision, our method achieves state-of-the-art performance in both in-domain and out-of-domain novel view synthesis, even under extreme viewpoint changes and limited image overlap, and surpasses recent methods that rely on geometric supervision for relative pose estimation. By eliminating dependence on ground-truth poses, our method offers the scalability to leverage larger and more diverse datasets. Code and pretrained models will be available on our project page: https://ranrhuang.github.io/spfsplatv2/.