Camilo Cruz Gambardella

Jon McCormack, Camilo Cruz Gambardella, Nina Rajcic et al.

In recent years Generative Machine Learning systems have advanced significantly. A current wave of generative systems use text prompts to create complex imagery, video, even 3D datasets. The creators of these systems claim a revolution in bringing creativity and art to anyone who can type a prompt. In this position paper, we question the basis for these claims, dividing our analysis into three areas: the limitations of linguistic descriptions, implications of the dataset, and lastly, matters of materiality and embodiment. We conclude with an analysis of the creative possibilities enabled by prompt-based systems, asking if they can be considered a new artistic medium.

Cheng Zhang, Hanwen Liang, Donny Y. Chen et al.

Panoramic video generation has attracted growing attention due to its applications in virtual reality and immersive media. However, existing methods lack explicit motion control and struggle to generate scenes with large and complex motions. We propose PanFlow, a novel approach that exploits the spherical nature of panoramas to decouple the highly dynamic camera rotation from the input optical flow condition, enabling more precise control over large and dynamic motions. We further introduce a spherical noise warping strategy to promote loop consistency in motion across panorama boundaries. To support effective training, we curate a large-scale, motion-rich panoramic video dataset with frame-level pose and flow annotations. We also showcase the effectiveness of our method in various applications, including motion transfer and video editing. Extensive experiments demonstrate that PanFlow significantly outperforms prior methods in motion fidelity, visual quality, and temporal coherence. Our code, dataset, and models are available at https://github.com/chengzhag/PanFlow.

Cheng Zhang, Qianyi Wu, Camilo Cruz Gambardella et al.

Generative models, e.g., Stable Diffusion, have enabled the creation of photorealistic images from text prompts. Yet, the generation of 360-degree panorama images from text remains a challenge, particularly due to the dearth of paired text-panorama data and the domain gap between panorama and perspective images. In this paper, we introduce a novel dual-branch diffusion model named PanFusion to generate a 360-degree image from a text prompt. We leverage the stable diffusion model as one branch to provide prior knowledge in natural image generation and register it to another panorama branch for holistic image generation. We propose a unique cross-attention mechanism with projection awareness to minimize distortion during the collaborative denoising process. Our experiments validate that PanFusion surpasses existing methods and, thanks to its dual-branch structure, can integrate additional constraints like room layout for customized panorama outputs. Code is available at https://chengzhag.github.io/publication/panfusion.

Cheng Zhang, Haofei Xu, Qianyi Wu et al.

With the advent of portable 360° cameras, panorama has gained significant attention in applications like virtual reality (VR), virtual tours, robotics, and autonomous driving. As a result, wide-baseline panorama view synthesis has emerged as a vital task, where high resolution, fast inference, and memory efficiency are essential. Nevertheless, existing methods are typically constrained to lower resolutions (512 $\times$ 1024) due to demanding memory and computational requirements. In this paper, we present PanSplat, a generalizable, feed-forward approach that efficiently supports resolution up to 4K (2048 $\times$ 4096). Our approach features a tailored spherical 3D Gaussian pyramid with a Fibonacci lattice arrangement, enhancing image quality while reducing information redundancy. To accommodate the demands of high resolution, we propose a pipeline that integrates a hierarchical spherical cost volume and Gaussian heads with local operations, enabling two-step deferred backpropagation for memory-efficient training on a single A100 GPU. Experiments demonstrate that PanSplat achieves state-of-the-art results with superior efficiency and image quality across both synthetic and real-world datasets. Code is available at https://github.com/chengzhag/PanSplat.

Jon McCormack, Camilo Cruz Gambardella

Many creative generative design spaces contain multiple regions with individuals of high aesthetic value. Yet traditional evolutionary computing methods typically focus on optimisation, searching for the fittest individual in a population. In this paper we apply quality-diversity search methods to explore a creative generative system (an agent-based line drawing model). We perform a random sampling of genotype space and use individual artist-assigned evaluations of aesthetic quality to formulate a computable fitness measure specific to the artist and this system. To compute diversity we use a convolutional neural network to discriminate features that are dimensionally reduced into two dimensions. We show that the quality-diversity search is able to find multiple phenotypes of high aesthetic value. These phenotypes show greater diversity and quality than those the artist was able to find using manual search methods.

Jon McCormack, Camilo Cruz Gambardella

In this paper we examine the concept of complexity as it applies to generative and evolutionary art and design. Complexity has many different, discipline specific definitions, such as complexity in physical systems (entropy), algorithmic measures of information complexity and the field of "complex systems". We apply a series of different complexity measures to three different evolutionary art datasets and look at the correlations between complexity and individual aesthetic judgement by the artist (in the case of two datasets) or the physically measured complexity of generative 3D forms. Our results show that the degree of correlation is different for each set and measure, indicating that there is no overall "better" measure. However, specific measures do perform well on individual datasets, indicating that careful choice can increase the value of using such measures. We then assess the value of complexity measures for the audience by undertaking a large-scale survey on the perception of complexity and aesthetics. We conclude by discussing the value of direct measures in generative and evolutionary art, reinforcing recent findings from neuroimaging and psychology which suggest human aesthetic judgement is informed by many extrinsic factors beyond the measurable properties of the object being judged.

Camilo Cruz Gambardella, Jon McCormack

The use of evolutionary methods in design and art is increasing in diversity and popularity. Approaches to using these methods for creative production typically focus either on optimisation or exploration. In this paper we introduce an evolutionary system for design that combines these two approaches, enabling users to explore landscapes of design alternatives using design-oriented measures of fitness, along with their own aesthetic preferences. We test our methods using a biologically-inspired generative system capable of producing 3D objects that can be exported directly as 3D printing toolpath instructions. For the search stage of our system we combine the use of the CMA-ES algorithm for optimisation and linear interpolation between generated objects for feature exploration. We investigate the system`s capabilities by evolving highly fit artefacts and then combining them with aesthetically interesting ones.

Jon McCormack, Camilo Cruz Gambardella, Andy Lomas

In this paper we examine the concept of complexity as it applies to generative art and design. Complexity has many different, discipline specific definitions, such as complexity in physical systems (entropy), algorithmic measures of information complexity and the field of "complex systems". We apply a series of different complexity measures to three different generative art datasets and look at the correlations between complexity and individual aesthetic judgement by the artist (in the case of two datasets) or the physically measured complexity of 3D forms. Our results show that the degree of correlation is different for each set and measure, indicating that there is no overall "better" measure. However, specific measures do perform well on individual datasets, indicating that careful choice can increase the value of using such measures. We conclude by discussing the value of direct measures in generative and evolutionary art, reinforcing recent findings from neuroimaging and psychology which suggest human aesthetic judgement is informed by many extrinsic factors beyond the measurable properties of the object being judged.