We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| nvlabs/long-video-gan | canonical | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| list_video_paths | Ran | nvlabs/long-video-gan/dataset_tools/make_dataset_from_videos.py pointer only (licence: NOASSERTION) · get_code("c45150eda6a7551b") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time while maintaining consistencies expected in real environments, such as plausible dynamics and object persistence. A common failure case is for content to never change due to over-reliance on inductive biases to provide temporal consistency, such as a single latent code that dictates content for the entire video. On the other extreme, without long-term consistency, generated videos may morph unrealistically between different scenes. To address these limitations, we prioritize the time axis by redesigning the temporal latent representation and learning long-term consistency from data by training on longer videos. To this end, we leverage a two-phase training strategy, where we separately train using longer videos at a low resolution and shorter videos at a high resolution. To evaluate the capabilities of our model, we introduce two new benchmark datasets with explicit focus on long-term temporal dynamics.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2206.03429")
get_code_for_paper("2206.03429")
have("2206.03429")
Connect an agent — have() is free.