GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis
Dynamic scene reconstruction with 3D Gaussian Splatting requires a balance between fine-grained motion modeling, structural stability, and compact representation. Existing per-primitive methods provide flexible local deformation but often suffer from redundant primitive growth, while anchor-based methods improve spatial regularity at the cost of suppressing locally varying motion. To address these issues, we present GrainGS, a dynamic Gaussian framework that combines a hierarchical anchor scaffold with per-Gaussian deformation. A static warm-up stage first establishes a time-invariant canonica
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%mudler/LocalAI →
“Shared author/contributor keys: guo”
- LinkedLinked via arxiv author · 85%Jiahao He →
“GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis”
- LinkedLinked via arxiv author · 85%Yihua Shao →
“GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis”
- LinkedLinked via arxiv author · 85%Zhengkai Zhao →
“GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis”
- LinkedLinked via arxiv author · 85%Pan Gao →
“GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis”
- LinkedLinked via arxiv author · 85%Tengfei Ma →
“GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis”
- LinkedLinked via arxiv author · 85%Jingcai Guo →
“GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis”
- LinkedLinked via arxiv author · 85%Hao Tang →
“GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis”