Signals 4 · free daily AI digest

SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting

Paper recorded by Signals 4 on 2026-08-31 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-31 on arXiv · recorded by Signals 4 on 2026-09-01

Category: cs.CV · 计算机视觉 · first seen 2026-09-01

Abstract

We study dynamic Gaussian Splatting from monocular videos. While recent advancements in dynamic Gaussian splatting offer a promising foundation for modeling dynamic scenes, they often overfit to the training views and fail under occlusion or complex scene motion due to the lack of reliable regularization signals in under-constrained regions. We propose Semantic Motion Graph (SMG), a novel approach

Read on arXiv →

#203 most recent of 237 cs.CV papers we have recorded · ↑ newer: Analytic Dynamics: Learning Physics-Grounded Representation for Fast I · ↓ older: From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for L
Cite this page: SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting: the #203 most recent of 237 cs.CV papers we have recorded (as of 2026-08-31). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/smg-semantic-motion-graph-for-monocular-dynamic-gaussian-splatting.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions