Picbreeder: evolving pictures collaboratively online

By Jimmy Secretan, Nicholas Beato. 2008

235 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Generative Models

Citations in the corpus

Deep Reinforcement Learning from Human Preferences (2017, background): “, 2014), and optimizing using human preferences in settings other than reinforcement learning (Machwe and Parmee, 2006; Secretan et al., 2008; Brochu et al., 2010; Sørensen et al., 2016).”
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains (2020, background): “The 2D image regression case (Figure 1b) has historically been limited in its practical use to artistic image synthesis [15, 39] and synthesizing images designed to mislead classifiers [31].”
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images (2014, background): “Specifically, the indirect encoding here is a compositional pattern-producing network (CPPN), which can evolve complex, regular images that resemble natural and man-made objects [25, 28, 1].”
Ieee Transactions on Evolutionary Computation on the Performance of Indirect Encoding across the Continuum of Regularity (unknown): “2) [24].”
Guided self-organization in indirectly encoded and evolving topographic maps (2014, background): “In effect, the indirect CPPN encoding can compactly encode patterns with regularities such as symmetry, repetition, and repetition with variation [20, 25].”
Search-Based Procedural Content Generation: A Taxonomy and Survey (2011, unknown): “Another good example is Elite, discussed above.”
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution (2023, background): “Promptbreeder is related to Picbreeder (Secretan et al., 2008), an open-ended human-in-the-loop system that evolves increasingly interesting images.”
Breeding a diversity of Super Mario behaviors through interactive evolution (2016, unknown): “Several examples of combining NE and IEC exist, such as users evolving 2D pictures in Picbreeder [16], 3D models through EndlessForms [2] or sound timbres [6].”
Data-efficient neuroevolution with kernel-based surrogate models (2018, background): “ther than their likelihood over the entire training set. NEAT is used to evolve compositional pattern producing networks (CPPNs) [27] , indirect encodings used to produce neural networks [29], images [16, 24], and solid objects [6]. Whether our approach is as successful in evolving indirect encoding”
Generative Art Using Neural Visual Grammars and Dual Encoders (2021, methodology): “The system is very diﬀerent from CPPNs which have been extensively used previously to evolve images [31] in that it uses a vastly more ineﬃcient recurrent neural network rather than generating the image in one go.”
Spatial PixelCNN: Generating Images from Patches (2017, background): “CPPNs have been shown to impose a strong spatial prior yielding images of highly regular patterns (Secretan et al., 2008; Nguyen et al., 2015).”
Human computation: a survey and taxonomy of a growing field (2011, methodology): “A simpler example is PicBreeder, where users evolve interesting graphical patterns by choosing among computer-generated choices [55].”