MrNeRF (@janusch_patas)
2025-12-14 | โค๏ธ 139 | ๐ 21
[SIGGRAPH Asia โ25] Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Video
Abstract: We introduce a fully automatic pipeline for dynamic scene reconstruction from casually captured monocular RGB videos. Rather than designing a new scene representation, we enhance the priors that drive Dynamic Gaussian Splatting.
Video segmentation combined with epipolar-error maps yields object-level masks that closely follow thin structures. These masks (i) guide an object-depth loss that sharpens the consistent video depth, and (ii) support skeleton-based sampling plus mask-guided re-identification to produce reliable, comprehensive 2-D tracks.
Two additional objectives embed the refined priors in the reconstruction stage:
- A virtual-view depth loss removes floaters.
- A scaffold-projection loss ties motion nodes to the tracks, preserving fine geometry and coherent motion.
The resulting system surpasses previous monocular dynamic scene reconstruction methods and delivers visibly superior renderings.
๋ฏธ๋์ด
