PM-Loss, a regularization technique using pointmaps from a pre-trained transformer, enhances feed-forward 3D Gaussian Splatting by improving depth map accuracy and rendering quality.
Depth maps are widely used in feed-forward 3D Gaussian Splatting (3DGS)
pipelines by unprojecting them into 3D point clouds for novel view synthesis.
This approach offers advantages such as efficient training, the use of known
camera poses, and accurate geometry estimation. However, depth discontinuities
at object boundaries often lead to fragmented or sparse point clouds, degrading
rendering quality — a well-known limitation of depth-based representations. To
tackle this issue, we introduce PM-Loss, a novel regularization loss based on a
pointmap predicted by a pre-trained transformer. Although the pointmap itself
may be less accurate than the depth map, it effectively enforces geometric
smoothness, especially around object boundaries. With the improved depth map,
our method significantly improves the feed-forward 3DGS across various
architectures and scenes, delivering consistently better rendering results. Our
project page: https://aim-uofa.github.io/PMLoss
