We present mean-shift distillation, a novel diffusion distillation technique that provides a provably good proxy for the gradient of the diffusion output distribution. This is derived directly from mean-shift mode seeking on the distribution, and we show that its extrema are aligned with the modes. We further derive an efficient product distribution sampling procedure to evaluate the gradient. Our method is formulated as a drop-in replacement for score distillation sampling (SDS), requiring neither model retraining nor extensive modification of the sampling procedure. We show that it exhibits superior mode alignment as well as improved convergence in both synthetic and practical setups, yielding higher-fidelity results when applied to both text-to-image and text-to-3D applications with Stable Diffusion.

UIST ’25, Busan, Republic of Korea

Abstract We present a fully automated technique that segments raster images into smooth shaded regions and reconstructs them using an optimal mix of solid fills, linear gradients, and radial gradients. Our method leverages a novel discontinuity‐aware segmentation strategy and gradient reconstruction algorithm to accurately capture intricate shading details and produce compact Bézier curve representations. Extensive evaluations on both designer‐created art and generative images demonstrate that our approach achieves high visual fidelity with minimal geometric complexity and fast processing times. This work offers a robust and versatile solution for converting detailed raster images into scalable vector graphics, addressing the evolving needs of modern design workflows.

The success of denoising diffusion models in representing rich data distributions over 2D raster images has prompted research on extending them to other data representations, such as vector graphics. Unfortunately due to their variable structure and scarcity of vector training data, directly applying diffusion models on this domain remains a challenging problem. Using workarounds like optimization via Score Distillation Sampling (SDS) is also fraught with difficulty, as vector representations are non-trivial to directly optimize and tend to result in implausible geometries such as redundant or self-intersecting shapes. NIVeL addresses these challenges by reinterpreting the problem on an alternative, intermediate domain which preserves the desirable properties of vector graphicsmainly sparsity of representation and resolution-independence. This alternative domain is based on neural implicit fields expressed in a set of decomposable, editable layers. Based on our experiments, NIVeL produces text-to- vector graphics results of significantly better quality than the state-of-the-art.

We present ChunkyGAN—a novel paradigm for modeling and editing images using generative adversarial networks. Unlike previous techniques seeking a global latent representation of the input image, our approach subdivides the input image into a set of smaller components (chunks) specified either manually or automatically using a pre-trained segmentation network. For each chunk, the latent code of a generative network is estimated locally with greater accuracy thanks to a smaller number of constraints. Moreover, during the optimization of latent codes, segmentation can further be refined to improve matching quality. This process enables high-quality projection of the original image with spatial disentanglement that previous methods would find challenging to achieve. To demonstrate the advantage of our approach, we evaluated it quantitatively and also qualitatively in various image editing scenarios that benefit from the higher reconstruction quality and local nature of the approach. Our method is flexible enough to manipulate even out-of-domain images that would be hard to reconstruct using global techniques.

Vector graphics are widely used to represent fonts, logos, digital artworks, and graphic designs. But, while a vast body of work has focused on generative algorithms for raster images, only a handful of options exists for vector graphics. One can always rasterize the input graphic and resort to image-based generative approaches, but this negates the advantages of the vector representation. The current alternative is to use specialized models that require explicit supervision on the vector graphics representation at training time. This is not ideal because large-scale high-quality vector-graphics datasets are difficult to obtain. Furthermore, the vector representation for a given design is not unique, so models that supervise on the vector representation are unnecessarily constrained. Instead, we propose a new neural network that can generate complex vector graphics with varying topologies, and only requires indirect supervision from readily-available raster training images (i.e., with no vector counterparts). To enable this, we use a differentiable rasterization pipeline that renders the generated vector shapes and composites them together onto a raster canvas. We demonstrate our method on a range of datasets, and provide comparison with state-of-the-art SVG-VAE and DeepSVG, both of which require explicit vector graphics supervision. Finally, we also demonstrate our approach on the MNIST dataset, for which no groundtruth vector representation is available. Source code, datasets and more results are available at http://geometry.cs.ucl.ac.uk/projects/2021/Im2Vec/.

Character design is a lengthy process, requiring artists to iteratively alter their characters' features and colorization schemes according to feedback from creative directors or peers. Artists experiment with multiple colorization schemes before deciding on the right color palette. This process may necessitate several tedious manual re-colorizations of the character. Any substantial changes to the character's appearance may also require manual re-colorization. Such complications motivate a computational approach for visualizing characters and drafting solutions. We propose a character exploration tool that automatically colors a sketch based on a selected style. The tool employs a Generative Adversarial Network trained to automatically color sketches. The tool also allows a selection of faces to be used as a template for the character's design. We validated our tool by comparing it with using Photoshop for character exploration in our pilot study. Finally, we conducted a study to evaluate our tool's efficacy within the design pipeline.

Abstract We present an approach to example‐based stylization of images that uses a single pair of a source image and its stylized counterpart. We demonstrate how to train an image translation network that can perform real‐time semantically meaningful style transfer to a set of target images with similar content as the source image. A key added value of our approach is that it considers also consistency of target images during training. Although those have no stylized counterparts, we constrain the translation to keep the statistics of neural responses compatible with those extracted from the stylized source. In contrast to concurrent techniques that use a similar input, our approach better preserves important visual characteristics of the source style and can deliver temporally stable results without the need to explicitly handle temporal consistency. We demonstrate its practical utility on various applications including video stylization, style transfer to panoramas, faces, and 3D models.

We introduce a differentiable rasterizer that bridges the vector graphics and raster image domains, enabling powerful raster-based loss functions, optimization procedures, and machine learning techniques to edit and generate vector content. We observe that vector graphics rasterization is differentiable after pixel prefiltering. Our differentiable rasterizer offers two prefiltering options: an analytical prefiltering technique and a multisampling anti-aliasing technique. The analytical variant is faster but can suffer from artifacts such as conflation. The multisampling variant is still efficient, and can render high-quality images while computing unbiased gradients for each pixel with respect to curve parameters. We demonstrate that our rasterizer enables new applications, including a vector graphics editor guided by image metrics, a painterly rendering algorithm that fits vector primitives to an image by minimizing a deep perceptual loss function, new vector graphics editing algorithms that exploit well-known image processing methods such as seam carving, and deep generative models that generate vector content from raster-only supervision under a VAE or GAN training objective.

This paper addresses the problem of interpolating visual textures. We formulate this problem by requiring (1) by-example controllability and (2) realistic and smooth interpolation among an arbitrary number of texture samples. To solve it we propose a neural network trained simultaneously on a reconstruction task and a generation task, which can project texture examples onto a latent space where they can be linearly interpolated and projected back onto the image domain, thus ensuring both intuitive control and realistic results. We show our method outperforms a number of baselines according to a comprehensive suite of metrics as well as a user study. We further show several applications based on our technique, which include texture brush, texture dissolve, and animal hybridization.

Abstract We present StyleBlit—an efficient example‐based style transfer algorithm that can deliver high‐quality stylized renderings in real‐time on a single‐core CPU. Our technique is especially suitable for style transfer applications that use local guidance ‐ descriptive guiding channels containing large spatial variations. Local guidance encourages transfer of content from the source exemplar to the target image in a semantically meaningful way. Typical local guidance includes, e.g., normal values, texture coordinates or a displacement field. Contrary to previous style transfer techniques, our approach does not involve any computationally expensive optimization. We demonstrate that when local guidance is used, optimization‐based techniques converge to solutions that can be well approximated by simple pixel‐level operations. Inspired by this observation, we designed an algorithm that produces results visually similar to, if not better than, the state‐of‐the‐art, and is several orders of magnitude faster. Our approach is suitable for scenarios with low computational budget such as games and mobile applications.

We introduce a new example-based approach to video stylization, with a focus on preserving the visual quality of the style, user controllability and applicability to arbitrary video. Our method gets as input one or more keyframes that the artist chooses to stylize with standard painting tools. It then automatically propagates the stylization to the rest of the sequence. To facilitate this while preserving visual quality, we developed a new type of guidance for state-of-art patch-based synthesis, that can be applied to any type of video content and does not require any additional information besides the video itself and a user-specified mask of the region to be stylized. We further show a temporal blending approach for interpolating style between keyframes that preserves texture coherence, contrast and high frequency details. We evaluate our method on various scenes from real production setting and provide a thorough comparison with prior art.

Since the advent of consumer photography, tourists and hikers have made photo records of their trips to share later. Aside from being kept as memories, photo presentations such as slideshows are also shown to others who have not visited the location to try to convey the experience.However, a slideshow alone is limited in conveying the broader spatial context, and thus the feeling of presence in beautiful natural scenery is lost. We address this by presenting the photographs as part of an immersive experience. We introduce an automated pipeline for aligning photographs with a digital terrain model. From this geographic registration, we produce immersive presentations which are viewed either passively as a video, or interactively in virtual reality. Our experimental evaluation verifies that this new mode of presentation successfully conveys the spatial context of the scene and is enjoyable to users.

We introduce a novel approach to example-based stylization of portrait videos that preserves both the subject's identity and the visual richness of the input style exemplar. Unlike the current state-of-the-art based on neural style transfer [Selim et al. 2016], our method performs non-parametric texture synthesis that retains more of the local textural details of the artistic exemplar and does not suffer from image warping artifacts caused by aligning the style exemplar with the target face. Our method allows the creation of videos with less than full temporal coherence [Ruder et al. 2016]. By introducing a controllable amount of temporal dynamics, it more closely approximates the appearance of real hand-painted animation in which every frame was created independently. We demonstrate the practical utility of the proposed solution on a variety of style exemplars and target videos.

Natural images often exhibit symmetries that should be taken into account when editing them. In this paper we present Nautilus --- a method for automatically identifying symmetric regions in an image along with their corresponding symmetry transformations. We compute dense local similarity symmetry transformations using a novel variant of the Generalised PatchMatch algorithm that uses Metropolis-Hastings sampling. We combine and refine these local symmetries using an extended Lucas-Kanade algorithm to compute regional transformations and their spatial extents. Our approach produces dense estimates of complex symmetries that are combinations of translation, rotation, scale, and reflection under perspective distortion. This enables a number of automatic symmetry-aware image editing applications including inpainting, rectification, beautification, and segmentation, and we demonstrate state-of-the-art applications for each of them.

We present an approach to example-based stylization of 3D renderings that better preserves the rich expressiveness of hand-created artwork. Unlike previous techniques, which are mainly guided by colors and normals, our approach is based on light propagation in the scene. This novel type of guidance can distinguish among context-dependent illumination effects, for which artists typically use different stylization techniques, and delivers a look closer to realistic artwork. In addition, we demonstrate that the current state of the art in guided texture synthesis produces artifacts that can significantly decrease the fidelity of the synthesized imagery, and propose an improved algorithm that alleviates them. Finally, we demonstrate our method's effectiveness on a variety of scenes and styles, in applications like interactive shading study or autocompletion.

In this paper we present Brushables—a novel approach to example-based painting that respects user-specified shapes at the global level and preserves textural details of the source image at the local level. We formulate the synthesis as a joint optimization problem that simultaneously synthesizes the interior and the boundaries of the region, transferring relevant content from the source to meaningful locations in the target. We also provide an intuitive interface to control both local and global direction of textural details in the synthesized image. A key advantage of our approach is that it enables a “combing” metaphor in which the user can incrementally modify the target direction field to achieve the desired look. Based on this, we implement an interactive texture painting tool capable of handling more complex textures than ever before, and demonstrate its versatility on difficult inputs including vegetation, textiles, hair and painting media.

Abstract We present an example‐based approach to rendering hand‐colored animations which delivers visual richness comparable to real artwork while enabling control over the amount of perceived temporal noise. This is important both for artistic purposes and viewing comfort, but is tedious or even intractable to achieve manually. We analyse typical features of real hand‐colored animations and propose an algorithm that tries to mimic them using only static examples of drawing media. We apply the algorithm to various animations using different drawing media and compare the quality of synthetic results with real artwork. To verify our method perceptually, we conducted experiments confirming that our method delivers distinguishable noise levels and reduces eye strain. Finally, we demonstrate the capabilities of our method to mask imperfections such as shower‐door artifacts.

In this paper we propose a reinterpretation of the brush and the fill tools for digital image painting. The core idea is to provide an intuitive approach that allows users to paint in the visual style of arbitrary example images. Rather than a static library of colors, brushes, or fill patterns, we offer users entire images as their palette, from which they can select arbitrary contours or textures as their brush or fill tool in their own creations. Compared to previous example-based techniques related to the painting-by-numbers paradigm we propose a new strategy where users can generate salient texture boundaries by our randomized graph-traversal algorithm and apply a content-aware fill to transfer textures into the delimited regions. This workflow allows users of our system to intuitively create visually appealing images that better preserve the visual richness and fluidity of arbitrary example images. We demonstrate the potential of our approach in various applications including interactive image creation, editing and vector image stylization.