ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation Paper • 2503.22194 • Published 7 days ago • 22
VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors Paper • 2503.01107 • Published Mar 3 • 2
Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models Paper • 2503.20240 • Published 10 days ago • 21
Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing Paper • 2503.19385 • Published 10 days ago • 32
SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions Paper • 2306.05178 • Published Jun 8, 2023 • 7