Patch-based 3D Natural Scene Generation from a Single Example

by   Weiyu Li, et al.

We target a 3D generative model for general natural scenes that are typically unique and intricate. Lacking the necessary volumes of training data, along with the difficulties of having ad hoc designs in presence of varying scene characteristics, renders existing setups intractable. Inspired by classical patch-based image models, we advocate for synthesizing 3D scenes at the patch level, given a single example. At the core of this work lies important algorithmic designs w.r.t the scene representation and generative patch nearest-neighbor module, that address unique challenges arising from lifting classical 2D patch-based framework to 3D generation. These design choices, on a collective level, contribute to a robust, effective, and efficient model that can generate high-quality general natural scenes with both realistic geometric structure and visual appearance, in large quantities and varieties, as demonstrated upon a variety of exemplar scenes.


page 6

page 7

page 13

page 14

page 20

page 21

page 22

page 23


SinGRAV: Learning a Generative Radiance Volume from a Single Natural Scene

We present a 3D generative model for general natural scenes. Lacking nec...

SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene

Generative models have shown great promise in synthesizing photorealisti...

Diverse Generation from a Single Video Made Possible

Most advanced video generation and manipulation methods train on a large...

Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks

State-of-the-art generative model-based attacks against image classifier...

A Latent Source Model for Patch-Based Image Segmentation

Despite the popularity and empirical success of patch-based nearest-neig...

Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval

In this work, by re-examining the "matching" nature of Anomaly Detection...

Learning Continuous Implicit Representation for Near-Periodic Patterns

Near-Periodic Patterns (NPP) are ubiquitous in man-made scenes and are c...

Please sign up or login with your details

Forgot password? Click here to reset