Translations:Diffusion Models Are Real-Time Game Engines/59/en: Difference between revisions

Latest revision as of 03:06, 7 September 2024

Information about message (contribute)

This message has no documentation. If you know where or how this message is used, you can help other translators by adding documentation to this message.

Message definition (Diffusion Models Are Real-Time Game Engines)

We therefore measure the FVD (Unterthiner et al., [https://arxiv.org/html/2408.14837v1#bib.bib35 2019]) computed over a random holdout of 512 trajectories, measuring the distance between the predicted and ground truth trajectory distributions, for simulations of length 16 frames (0.8 seconds) and 32 frames (1.6 seconds). For 16 frames, our model obtains an FVD of <math>114.02</math>. For 32 frames, our model obtains an FVD of <math>186.23</math>.

We therefore measure the FVD (Unterthiner et al., 2019) computed over a random holdout of 512 trajectories, measuring the distance between the predicted and ground truth trajectory distributions, for simulations of length 16 frames (0.8 seconds) and 32 frames (1.6 seconds). For 16 frames, our model obtains an FVD of $114.02$ . For 32 frames, our model obtains an FVD of $186.23$ .

Revision as of 05:28, 1 September 2024 (view source) FuzzyBot (talk \| contribs) (Importing a new version from external source)		Latest revision as of 03:06, 7 September 2024 (view source) FuzzyBot (talk \| contribs) (Importing a new version from external source)
Line 1:		Line 1:
	We therefore measure the FVD (Unterthiner ~~et al~~., [https://arxiv.org/html/2408.14837v1#bib.bib35 2019]) computed over a random holdout of 512 trajectories, measuring the distance between the predicted and ground truth trajectory distributions, for simulations of length 16 frames (0.8 seconds) and 32 frames (1.6 seconds). For 16 frames, our model obtains an FVD of <math>114.02</math>. For 32 frames, our model obtains an FVD of <math>186.23</math>.		We therefore measure the FVD (Unterthiner et al., [https://arxiv.org/html/2408.14837v1#bib.bib35 2019]) computed over a random holdout of 512 trajectories, measuring the distance between the predicted and ground truth trajectory distributions, for simulations of length 16 frames (0.8 seconds) and 32 frames (1.6 seconds). For 16 frames, our model obtains an FVD of <math>114.02</math>. For 32 frames, our model obtains an FVD of <math>186.23</math>.