arXiv Computer Vision
SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
3d ago
SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting
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 t...
arXiv AI
2d ago
RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos
arXiv:2608.29003v1 Announce Type: cross Abstract: In dynamic and unstructured environments, conventional SLAM systems generally suffer from significant accuracy degeneration due to their static assum...
arXiv AI
Jul 16
ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding
arXiv:2607. 13421v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression.
arXiv Computer Vision
2d ago
ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation
arXiv:2608.30184v1 Announce Type: new Abstract: Volumetric video enables immersive free viewpoint rendering of dynamic real world scenes, yet existing methods struggle with long sequences and complex...
arXiv AI
Aug 25
Learning Implicit Constitutive Laws for Dynamic 3D Gaussian Splatting from Monocular Videos
arXiv:2608.22102v1 Announce Type: cross Abstract: We present GCA (Gaussian Constitutive Alignment), a framework for learning implicit constitutive laws from monocular dynamic video of deformable obje...
arXiv Computer Vision
Aug 27
Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos
Forge4D is a feed‑forward model that reconstructs temporally aligned 4D human representations from uncalibrated sparse‑view videos, enabling both novel view and novel time synthesis. It achieves this by jointly streaming 3D Gaussian reconstruction with dense motion prediction, using learnable state tokens for temporal consistency and a self‑supervised retargeting loss for motion prediction. Extensive experiments confirm its effectiveness on in‑domain and out‑of‑domain datasets.