/AI17h ago

Waymo and XPeng use generative video models to synthesize multi-camera surround-view training data from a single front-facing dashcam video

The synthetic data generation method was demonstrated at CVPR.

--0--
Original posts
Comments
Original post
Andrei Bursuc @CVPR@abursuc#1577inAI

An emerging application of video generative models for autonomous driving to augment data: given a dashcam/frontcam video, generate the surround camera views video. Huge amounts of such videos online or at specific suppliers. Both Waymo and Xpeng showed such approaches #cvpr2026

2:57 PM · Jun 3, 2026 · 3.5K Views
Sentiment
Sentiment building, check back later.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
VIEWS1.3KBOOKMARKS1LIKES3RETWEETS1

@abursuc This is a very nice and easy to convey example of synthetic data, thanks for sharing I'll definitely use it in some future explanations !

An emerging application of video generative models for autonomous driving to augment data: given a dashcam/frontcam video, generate the surround camera views video. Huge amounts of such videos online or at specific suppliers. Both Waymo and Xpeng showed such approaches #cvpr2026

8hViews 1.3KLikes 3Bookmarks 1