ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion
3D Gaussian Splatting (3DGS) achieves high-quality novel-view synthesis by optimizing freely placed primitives in 3D and adaptively densifying them in under-reconstructed regions. However, this scene-adaptive capacity allocation is largely lost in existing feed-forward 3DGS methods, which commonly regress Gaussians at input pixels and lift them along camera rays. Such pixel-aligned formulations make the number and placement of primitives depend on image resolution and input viewpoints rather than scene complexity, resulting in dense and often redundant Gaussian sets. We present ATSplat, a feed
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%browser-use/browser-use →
“Shared author/contributor keys: lee”
- LinkedLinked via arxiv author · 85%Cho In →
“ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion”
- LinkedLinked via arxiv author · 85%Jeonghwan Cho →
“ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion”
- LinkedLinked via arxiv author · 85%Mijin Yoo →
“ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion”
- LinkedLinked via arxiv author · 85%Gim Hee Lee →
“ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion”
- LinkedLinked via arxiv author · 85%Seon Joo Kim →
“ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion”
- PossiblePossibly related (embedding) · 48%The Gaussian splatting tool "VRCGS" for VRChat has been updated to support rendering up to 100 million splatters. - Mogura VR →