Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
arXiv preprint arXiv:2507.12646 (2025)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
fields
cs.CV 4years
2026 4verdicts
UNVERDICTED 4roles
background 3polarities
background 3representative citing papers
Reshoot-Anything trains a diffusion transformer on pseudo multi-view triplets created by cropping and warping monocular videos to achieve temporally consistent video reshooting with robust camera control on dynamic scenes.
Video diffusion models can be adapted into permutation-invariant generators for sparse novel view synthesis by treating the problem as video completion and removing temporal order cues.
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.
citing papers explorer
-
Geo-Align: Video Generation Alignment via Metric Geometry Reward
Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
-
Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting
Reshoot-Anything trains a diffusion transformer on pseudo multi-view triplets created by cropping and warping monocular videos to achieve temporally consistent video reshooting with robust camera control on dynamic scenes.
-
Novel View Synthesis as Video Completion
Video diffusion models can be adapted into permutation-invariant generators for sparse novel view synthesis by treating the problem as video completion and removing temporal order cues.
-
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.