arXiv subjects

Steve Maddock

Publications and source records attributed to Steve Maddock.

10 recordsLinked to original sources

arXiv2026

SIC3D: Style Image Conditioned Text-to-3D Gaussian Splatting Generation

Recent progress in text-to-3D object generation enables the synthesis of detailed geometry from text input by leveraging 2D diffusion models and differentiable 3D representations. However, the approaches often suffer from limited controllability and texture ambiguity due to the limitation of the text modality. To address this, we present SIC3D, a controllable image-conditioned text-to-3D generation pipeline with 3D Gaussian Splatting (3DGS). There are two stages in SIC3D. The first stage generates the 3D object content from text with a text-to-3DGS generation model. The second stage transfers style from a reference image to the 3DGS. Within this stylization stage, we introduce a novel Variational Stylized Score Distillation (VSSD) loss to effectively capture both global and local texture patterns while mitigating conflicts between geometry and appearance. A scaling regularization is further applied to prevent the emergence of artifacts and preserve the pattern from the style image. Extensive experiments demonstrate that SIC3D enhances geometric fidelity and style adherence, outperforming prior approaches in both qualitative and quantitative evaluations.

cs.CV↗

arXiv2025

PQDAST: Depth-Aware Arbitrary Style Transfer for Games via Perceptual Quality-Guided Distillation

Artistic style transfer is concerned with the generation of imagery that combines the content of an image with the style of an artwork. In the realm of computer games, most work has focused on post-processing video frames. Some recent work has integrated style transfer into the game pipeline, but it is limited to single styles. Integrating an arbitrary style transfer method into the game pipeline is challenging due to the memory and speed requirements of games. We present PQDAST, the first solution to address this. We use a perceptual quality-guided knowledge distillation framework and train a compressed model using the FLIP evaluator, which substantially reduces both memory usage and processing time with limited impact on stylisation quality. For better preservation of depth and fine details, we utilise a synthetic dataset with depth and temporal considerations during training. The developed model is injected into the rendering pipeline to further enforce temporal stability and avoid diminishing post-process effects. Quantitative and qualitative experiments demonstrate that our approach achieves superior performance in temporal consistency, with comparable style transfer quality, to state-of-the-art image, video and in-game methods.

cs.CV↗

arXiv2024

The impact of differences in facial features between real speakers and 3D face models on synthesized lip motions

Lip motion accuracy is important for speech intelligibility, especially for users who are hard of hearing or second language learners. A high level of realism in lip movements is also required for the game and film production industries. 3D morphable models (3DMMs) have been widely used for facial analysis and animation. However, factors that could influence their use in facial animation, such as the differences in facial features between recorded real faces and animated synthetic faces, have not been given adequate attention. This paper investigates the mapping between real speakers and similar and non-similar 3DMMs and the impact on the resulting 3D lip motion. Mouth height and mouth width are used to determine face similarity. The results show that mapping 2D videos of real speakers with low mouth heights to 3D heads that correspond to real speakers with high mouth heights, or vice versa, generates less good 3D lip motion. It is thus important that such a mismatch is considered when using a 2D recording of a real actor's lip movements to control a 3D synthetic character.

cs.GR↗

arXiv2024

Evaluation in Neural Style Transfer: A Review

The field of Neural Style Transfer (NST) has witnessed remarkable progress in the past few years, with approaches being able to synthesize artistic and photorealistic images and videos of exceptional quality. To evaluate such results, a diverse landscape of evaluation methods and metrics is used, including authors' opinions based on side-by-side comparisons, human evaluation studies that quantify the subjective judgements of participants, and a multitude of quantitative computational metrics which objectively assess the different aspects of an algorithm's performance. However, there is no consensus regarding the most suitable and effective evaluation procedure that can guarantee the reliability of the results. In this review, we provide an in-depth analysis of existing evaluation techniques, identify the inconsistencies and limitations of current evaluation methods, and give recommendations for standardized evaluation practices. We believe that the development of a robust evaluation framework will not only enable more meaningful and fairer comparisons among NST methods but will also enhance the comprehension and interpretation of research findings in the field.

cs.CV↗

arXiv2023

Neural Style Transfer for Computer Games

Neural Style Transfer (NST) research has been applied to images, videos, 3D meshes and radiance fields, but its application to 3D computer games remains relatively unexplored. Whilst image and video NST systems can be used as a post-processing effect for a computer game, this results in undesired artefacts and diminished post-processing effects. Here, we present an approach for injecting depth-aware NST as part of the 3D rendering pipeline. Qualitative and quantitative experiments are used to validate our in-game stylisation framework. We demonstrate temporally consistent results of artistically stylised game scenes, outperforming state-of-the-art image and video NST methods.

cs.CV↗

arXiv2023

Using The Polynomial Particle-In-Cell Method For Liquid-Fabric Interaction

Liquid-fabric interaction simulations using particle-in-cell (PIC) based models have been used to simulate a wide variety of phenomena and yield impressive visual results. However, these models suffer from numerical damping due to the data interpolation between the particles and grid. Our paper addresses this by using the polynomial PIC (PolyPIC) model instead of the affine PIC (APIC) model that is used in current state-of-the-art wet cloth models. The affine transfers of the APIC model are replaced by the higher order polynomials of PolyPIC, thus reducing numerical dissipation and improving resolution of vorticial details. This improved energy preservation enables more dynamic simulations to be generated although this is at an increased computational cost.

cs.GR↗

arXiv2022

Depth-aware Neural Style Transfer using Instance Normalization

Neural Style Transfer (NST) is concerned with the artistic stylization of visual media. It can be described as the process of transferring the style of an artistic image onto an ordinary photograph. Recently, a number of studies have considered the enhancement of the depth-preserving capabilities of the NST algorithms to address the undesired effects that occur when the input content images include numerous objects at various depths. Our approach uses a deep residual convolutional network with instance normalization layers that utilizes an advanced depth prediction network to integrate depth preservation as an additional loss function to content and style. We demonstrate results that are effective in retaining the depth and global structure of content images. Three different evaluation processes show that our system is capable of preserving the structure of the stylized results while exhibiting style-capture capabilities and aesthetic qualities comparable or superior to state-of-the-art methods. Project page: https://ioannoue.github.io/depth-aware-nst-using-in.html.

cs.CV↗

arXiv2020

Simulating Crowds and Autonomous Vehicles

Understanding how people view and interact with autonomous vehicles is important to guide future directions of research. One such way of aiding understanding is through simulations of virtual environments involving people and autonomous vehicles. We present a simulation model that incorporates people and autonomous vehicles in a shared urban space. The model is able to simulate many thousands of people and vehicles in real-time. This is achieved by use of GPU hardware, and through a novel linear program solver optimized for large numbers of problems on the GPU. The model is up to 30 times faster than the equivalent multi-core CPU model.

cs.RO↗

arXiv2019

Fast Simulation of Crowd Collision Avoidance

Real-time large-scale crowd simulations with realistic behavior, are important for many application areas. On CPUs, the ORCA pedestrian steering model is often used for agent-based pedestrian simulations. This paper introduces a technique for running the ORCA pedestrian steering model on the GPU. Performance improvements of up to 30 times greater than a multi-core CPU model are demonstrated. This improvement is achieved through a specialized linear program solver on the GPU and spatial partitioning of information sharing. This allows over 100,000 people to be simulated in real time (60 frames per second).

cs.RO↗

arXiv2019

Two-Dimensional Batch Linear Programming on the GPU

This paper presents a novel, high-performance, graphical processing unit-based algorithm for efficiently solving two-dimensional linear programs in batches. The domain of two-dimensional linear programs is particularly useful due to the prevalence of relevant geometric problems. Batch linear programming refers to solving numerous different linear programs within one operation. By solving many linear programs simultaneously and distributing workload evenly across threads, graphical processing unit utilization can be maximized. Speedups of over 22 times and 63 times are obtained against state-of-the-art graphics processing unit and CPU linear program solvers, respectively.

cs.DC↗