Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections

Understand

Novel view synthesis from unconstrained in-the-wild images remains a meaningful but challenging task.

• The photometric variation and transient occluders in those unconstrained images make it difficult to reconstruct the original scene accurately.
• Previous approaches tackle the problem by introducing a global appearance feature in Neural Radiance Fields (NeRF).
• However, in the real world, the unique appearance of each tiny point in a scene is determined by its independent intrinsic material attributes and the varying environmental impacts it receives.