DENSER: Depth-Guided Ensemble with Staged EFA-GS Reconstruction for Soccer Novel View Synthesis
Improves novel view synthesis for soccer broadcast applications by addressing textureless regions and ground-level view quality.
DENSER extends EFA-GS with depth-guided ensemble and staged reconstruction for soccer novel view synthesis, achieving 29.89 dB PSNR, 0.791 SSIM, and 0.366 LPIPS on five held-out scenes.
We propose DENSER, a Depth-guided ENSemble with Staged EFA-GS Reconstruction for soccer novel view synthesis. DENSER extends EFA-GS with three key contributions: (1) camera-height-based loss weighting that prioritises ground-level broadcast views, (2) monocular depth supervision from Depth-Anything-V2 to regularise geometry in textureless regions, and (3) a three-model pixel-average ensemble whose members diverge from a shared base checkpoint by varying training length and Gaussian scale clamping. On five held-out challenge scenes we achieve a mean PSNR of 29.89 dB, SSIM of 0.791, and LPIPS of 0.366.