GenRec: Knowing Where to Reconstruct and Where to Generate
Generative novel view synthesis from sparse input images is rarely all reconstruction or all generation: pixels visible in some source view have a unique correct value modulated only by view-dependent shading, while pixels in disocclusions or beyond the captured volume admit a distribution of plausible completions. Existing generative novel-view-synthesis methods conflate these regimes under a single uniform loss, blurring the line between geometric fidelity and creative hallucinations even when scene geometry is injected through warped point clouds or projected depth. We introduce GenRec, a m
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%Ata Çelen →
“GenRec: Knowing Where to Reconstruct and Where to Generate”
- LinkedLinked via arxiv author · 85%Jaewoo Jung →
“GenRec: Knowing Where to Reconstruct and Where to Generate”
- LinkedLinked via arxiv author · 85%Federico Tombari →
“GenRec: Knowing Where to Reconstruct and Where to Generate”
- LinkedLinked via arxiv author · 85%Marc Pollefeys →
“GenRec: Knowing Where to Reconstruct and Where to Generate”
- LinkedLinked via arxiv author · 85%Sunghwan Hong →
“GenRec: Knowing Where to Reconstruct and Where to Generate”
- LinkedLinked via arxiv author · 85%Michael Niemeyer →
“GenRec: Knowing Where to Reconstruct and Where to Generate”
- LinkedLinked via arxiv author · 85%Daniel Barath →
“GenRec: Knowing Where to Reconstruct and Where to Generate”