LIVE achieves state-of-the-art instruction-based video editing by jointly training on image and video data with a frame-wise token noise strategy to bridge domain gaps and a new benchmark of over 60 tasks.
arXiv preprint arXiv:2508.06080 (2025)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
SpatialEdit provides a benchmark, large synthetic dataset, and baseline model for precise object and camera spatial manipulations in images, with the model beating priors on spatial editing.
A new occlusion-aware control module generates high-fidelity egocentric videos from sparse 3D hand joints, supported by a million-clip dataset and cross-embodiment benchmark.
citing papers explorer
-
LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing
LIVE achieves state-of-the-art instruction-based video editing by jointly training on image and video data with a frame-wise token noise strategy to bridge domain gaps and a new benchmark of over 60 tasks.
-
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
SpatialEdit provides a benchmark, large synthetic dataset, and baseline model for precise object and camera spatial manipulations in images, with the model beating priors on spatial editing.
-
Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints
A new occlusion-aware control module generates high-fidelity egocentric videos from sparse 3D hand joints, supported by a million-clip dataset and cross-embodiment benchmark.