WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images
While feedforward 3D reconstruction excels at efficient novel view synthesis, it typically falters when faced with scenes under varying illumination. To this end, we introduce WildSplat, the first feedforward 3D Gaussian Splatting framework capable of appearance-conditioned novel-view synthesis for unposed in-the-wild images. To handle inconsistent photometric conditions, we propose a dual-branch architecture that explicitly decouples geometry from appearance. The geometry branch extracts an appearance-invariant 3D structure and jointly predicts camera poses. To govern the rendering appearance
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.
- LinkedLinked via arxiv author · 85%Xiyu Zhang →
“WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images”
- LinkedLinked via arxiv author · 85%Jingyu Zhuang →
“WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images”
- LinkedLinked via arxiv author · 85%Hongjia Zhai →
“WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images”
- LinkedLinked via arxiv author · 85%Zizheng Yan →
“WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images”
- LinkedLinked via arxiv author · 85%Jinwei Chen →
“WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images”
- LinkedLinked via arxiv author · 85%Guofeng Zhang →
“WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images”
- LinkedLinked via arxiv author · 85%Qingnan Fan →
“WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images”