Return to site

ICCV 2022 Open Access Repository

Zekun Hao, Arun Mallya, Serge Belongie, Ming-Yu Liu; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021 (pp. 14072-14082


We present GANcraft, an unsupervised neural rendering framework that produces realistic images of large 3D block worlds, such as the ones created by Minecraft. Our method takes a semantic block world as an input which is assigned a semantic label , such as dirt, grass, or water. We represent the world as continuous volumetric functions and train our model to render view-consistent , photorealistic images for a user-controlled camera. In the absence of ground truth paired images for the block world, we propose an approach to training built on pseudo-ground reality and adversarial training. email is in contrast to previous research on neural rendering to assist view synthesizing. This requires ground truth images to establish the geometry of the scene as well as the appearance dependent on view. GANcraft allows users to control both scene semantics as well as output style. Comparing GANcraft to strong baselines proves the efficacy of GANcraft in this new area of photorealistic block world synthesizing.



All Posts

Almost done…

We just sent you an email. Please click the link in the email to confirm your subscription!

OKSubscriptions powered by Strikingly