Stitch-a-Demo is a retrieval-based method that assembles visually coherent video demonstrations from multistep textual descriptions by training on weakly supervised procedural data with hard negatives.
Video generation models as world simulators.OpenAI Blog, 1(8):1
2 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
fields
cs.CV 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on the TASTE-Rob dataset.
citing papers explorer
-
Stitch-a-Demo: Video Demonstrations from Multistep Descriptions
Stitch-a-Demo is a retrieval-based method that assembles visually coherent video demonstrations from multistep textual descriptions by training on weakly supervised procedural data with hard negatives.
-
HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis
HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on the TASTE-Rob dataset.