arXiv Computer Vision
ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it 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.
arXiv Computer Vision
Oct 8
Sparse-View 4D Gaussian Splatting via Spatiotemporal Priors and Generative Assistance
arXiv:2610.04606v2 Announce Type: replace Abstract: We present a 4D Gaussian Splatting framework for the Sparse-View Track of the SIGGRAPH Asia 2026 Volumetric Video Challenge, which requires dynamic...
arXiv AI
Jul 2
FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles
arXiv:2605. 03337v3 Announce Type: replace-cross Abstract: Recent progress in 4D Gaussian Splatting (4DGS) has achieved impressive dynamic scene reconstruction results.
arXiv Computer Vision
3d ago
Dusting the Phantom: Gaussian Allocation for Fading Dynamic Content
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.
arXiv Computer Vision
3d ago
Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation
Anchor3DGS introduces a pose‑free, feed‑forward 3D Gaussian Splatting framework that replaces pixel‑aligned Gaussian prediction with a compact anchor‑based representation. By placing 3D anchors guided by information entropy, the method concentrates primitives in visually complex regions while ensuring broad spatial coverage, and each anchor aggregates multi‑view features to generate local Gaussians. A lightweight feature enhancement module refines the coarse RGB output, resulting in state‑of‑the‑art novel view synthesis quality with an order of magnitude fewer Gaussian primitives than prior approaches.
Hugging Face Trending Papers
Jul 13
HyperGS: Fast and Generalizable Gaussian Video Representation
Gaussian Splatting has emerged as an effective representation for video, but existing methods rely on per-video optimization. This leads to slow encoding and limits generalization across videos.