The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.
arXiv preprint arXiv:2506.18890 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2roles
background 1polarities
background 1representative citing papers
LSRM scales transformer context windows with native sparse attention and geometric routing to deliver high-fidelity feed-forward 3D reconstruction and inverse rendering that approaches dense optimization quality.
citing papers explorer
-
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.
-
LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows
LSRM scales transformer context windows with native sparse attention and geometric routing to deliver high-fidelity feed-forward 3D reconstruction and inverse rendering that approaches dense optimization quality.