← Back to all news
arXiv Computer Vision By Minhyeok Roh, Minseo Lee, Jun Young Jeong, Byeonghyeon Lee, Lucas Yunkyu Lee, Jaesik Park, Eunbyung Park

Dusting the Phantom: Gaussian Allocation for Fading Dynamic Content

Read the original on arXiv Computer Vision →

The paper introduces two new strategies—Seed Injection and Temporal Biased Relocation—to improve Gaussian-based volumetric video reconstruction in highly dynamic scenes. Seed Injection detects under‑reconstructed regions by monitoring temporal appearance changes and reconstruction errors, then initializes new Gaussians at plausible 3D locations using multi‑view data, independent of existing Gaussian positions. Temporal Biased Relocation guides the placement of relocated Gaussians using time‑resolved optimization signals, all while keeping the Gaussian budget fixed. Experiments on multiple dynamic‑scene datasets show that these methods recover small, fast‑moving objects and fine appearance details that previous allocation strategies missed.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
3d ago

ResStreamGS: Residual-Sensitive Dual-Stream Gaussian Splatting for Mobile Volumetric Video Streaming

ResStreamGS introduces a residual‑sensitive dual‑stream framework for mobile volumetric video streaming that distinguishes temporally stable Gaussians from residual‑sensitive ones. Stable Gaussians are transmitted once per Group of Pictures, while only the residual‑sensitive Gaussians are included in the frame‑wise video stream, reducing bandwidth usage. Experiments on complex full‑scene videos show a 7.51–8.35 dB PSNR improvement over a V³‑style baseline, a payload reduction of up to 56.5%, and real‑time performance of 30.883 FPS on a Qualcomm Snapdragon 778G.

By Haoran Liu, Di Wu, Wang Luo, Hengyuan Na, Miao Hu, Guocong Quan
More like this →
arXiv Computer Vision
Sep 4

F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting

F4Splat introduces a feed‑forward predictive densification strategy for 3D Gaussian splatting that allocates Gaussians based on a densification‑score guided by spatial complexity and multi‑view overlap. The method predicts per‑region scores to estimate required Gaussian density, enabling explicit control over the total Gaussian budget without retraining. This adaptive allocation reduces redundancy in simple regions and minimizes duplicate Gaussians across overlapping views, yielding compact yet high‑quality 3D representations and superior novel‑view synthesis performance with fewer Gaussians.

By Injae Kim, Chaehyeon Kim, Minseong Bae, Minseok Joo, Hyunwoo J. Kim
More like this →