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.
Trajectorycrafter: Redirecting camera trajectory for monocular videos via diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Bernini is a framework that uses an MLLM planner to output semantic representations for a DiT renderer to generate or edit videos, reporting SOTA benchmark performance.
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.
-
Bernini: Latent Semantic Planning for Video Diffusion
Bernini is a framework that uses an MLLM planner to output semantic representations for a DiT renderer to generate or edit videos, reporting SOTA benchmark performance.