Papers for

video game artists

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Neural texture compression improves image quality with anisotropic filtering

Explicit LOD-Conditioned Anisotropic Filtering for Neural Texture Compression

Abstract: Neural texture compression (NTC) stores material textures compactly, but the dominant feature-pyramid design receives no filtering from the GPU texture unit: it learns each material at a fixed UV and level of detail and has no explicit anisotropic-filtering (AF) mechanism. Setting the filter from the footprint aspect ratio alone is not enough: a single input cannot carry both the shape of the footprint and its size, so the image is too blurry near the camera by the same amount at every distance. Our method, AF-NTC, instead conditions the decoder on the same three bounded values a hardware sampler uses: minor-axis scale (LOD), aspect ratio, and major-axis orientation. These drive a tap line along the major axis and a level blend across the minor axis, and we train against anisotropically filtered ground truth. At $25\%$ of a full BC7 mip chain, AF-NTC beats the no-AF trilinear-BC7 baseline on all ten material--scene pairs we compare ($+1.3$ to $+7.6$\,dB), and it is $0.0$ to $3.4$\,dB below the $4\times$-larger anisotropic-BC7, depending on the material.

Mon 9 NovGraphics
The gist
Neural texture compression saves space when storing material images but usually treats every detail the same, causing blurry images near the camera. The authors created a way to teach the system to understand how images look from different angles and distances by using three geometric values that hardware also uses. Their method, called AF-NTC, creates sharper textures at much smaller sizes compared to standard methods. This technique improves visual details without needing large amounts of storage.
Open → 2611.12650v1

Text-to-image models generate more varied images without losing quality

TokenRepel: Generating Diverse Image Sets Without Compromising Quality

Abstract: We present an inference-time approach that enhances the visual diversity of image sets generated by text-to-image models, without compromising the average image quality. Our method leverages the intrinsic geometry of hidden representations in pretrained models to diversify images generated from the same prompt. First, we introduce a token repulsion mechanism that increases the angle between feature tokens across samples. It takes a negative Riemannian gradient step on a von Mises-Fisher mixture distribution of tokens on the unit hypersphere. Second, to preserve the quality of each output image, we propose a token density preservation mechanism that projects the repulsion-induced prediction change onto a half-space aligned with the model's score direction. This encourages the updates to remain within the high-density regions learned by the generative model. We further extend this mechanism to the output of each intermediate layer, enabling finer-grained iterative guidance. We evaluate our method on three types of pretrained text-to-image models. Experiments show substantial gains in visual diversity under identical prompts, while maintaining a comparable level of image fidelity.

Thu 29 OctComputer Vision and Pattern Recognition
The gist
Sometimes, when computers make pictures from words, they create many images that all look very similar. The authors found a way to help these models produce a wider variety of images for the same text prompt while keeping the pictures looking good. They do this by making the computer representations inside the model push away from each other so the images differ more. They also make sure that the changes don’t make the pictures worse by keeping the computer’s predictions in a high-quality zone. This method works well with different types of text-to-image models.
Open → 2610.39913v1

SwitchSplat enables flexible 3D views of changing objects in scenes

SwitchSplat: Learning Discrete Object States from Casually Captured Scenes

Abstract: 3D Gaussian Splatting has made high-fidelity 3D reconstruction fast and accessible, yet existing representations assume a static world. This assumption breaks down in casual captures, where a user naturally interacts with the environment -- opening doors, toggling switches, or moving objects -- introducing discrete state changes that no current framework can model. Time-conditioned dynamic methods such as 4DGS conflate when a state was observed with what state the scene is in, limiting them to replaying seen sequences rather than composing arbitrary object configurations. We present SwitchSplat, the first 3DGS representation to address this gap via a base+slot decomposition: a shared static base captures the invariant scene, while each slot independently holds the two binary states (on/off) of one interactable object. Because the assignment of Gaussians to slots is fully differentiable, the model discovers the geometry of each state directly from video, without manual annotation. At inference, the user can freely combine slot states and render the resulting scene from any viewpoint. We validate SwitchSplat on a new casual-capture dataset and show that it outperforms static and dynamic baselines in novel-view synthesis quality, while uniquely supporting rendering of state combinations never seen during capture. Project page: https://switchsplat.github.io

Sat 17 OctComputer Vision and Pattern RecognitionGraphics
The gist
When people capture 3D scenes with objects that can move or change, such as doors opening or switches flipping, existing methods struggle to show these changes realistically. The authors developed SwitchSplat, a new way to represent scenes that separates static parts from objects that can switch between two states. This lets users combine these states freely to see new views of the scene, even configurations not seen before. SwitchSplat learns this from regular videos without needing any special labels or annotations.
Open → 2610.24812v1

Appearance aware matching improves texture interpolation quality

Texture Interpolation as Texton Matching

Abstract: Texture interpolation asks what should lie between two textures. Standard methods typically blend pixels or features at corresponding spatial locations, implicitly assuming that co-located elements should be mixed. For unrelated textures, however, this correspondence is arbitrary: a crack at one location has no particular relationship to a fiber at the same location in another image. We study whether this hidden pairing choice is itself a major determinant of interpolation quality. We represent textures as collections of local appearance vectors, or textons, and replace positional pairing with appearance-aware matching while keeping the encoder, representation, and decoder fixed. This isolates the effect of correspondence from changes in model capacity or training. Across texture pairs, appearance-aware matching consistently improves the distributional quality of interpolated midpoints over positional feature blending. Soft matching produces the strongest midpoint statistics, whereas one-to-one assignments yield more balanced transitions and closer agreement with the target endpoint. The same intervention also improves a second pretrained texture interpolator without retraining. These results identify correspondence as a first-class design choice in texture interpolation: meaningful transitions depend not only on how strongly two textures are mixed, but also on which local appearances are mixed with one another.

Tue 13 OctComputer Vision and Pattern RecognitionGraphicsMachine Learning
The gist
When blending two different textures, simply mixing points in the same spots often creates unrealistic results because those spots may represent unrelated features. The authors show that matching parts based on how they look, rather than where they are, makes the transition between textures look more natural. By focusing on matching similar local textures instead of just blending by position, the resulting mix better captures the feel of both textures. This approach works even without changing the texture-processing model, highlighting how important the matching choice is.
Open → 2610.18655v1

Matrix guided method creates editable 4d scenes from one image

MATE4D: Matrix-Guided Editable 4D Generation from a Single Image

Abstract: Generative models have rapidly pushed content creation be-yond 2D imagery toward dynamic 3D and 4D scene synthesis. Yet pro-ducing realistic and temporally stable 4D content from a single image is still difficult because one view provides limited structural cues and weak motion evidence. We introduce MATE4D, a framework that converts one input image into editable dynamic 4D content. Our method constructs a spatio-temporal multi-view image matrix with text-guided background manipulation, delivering coherent supervision over viewpoint, appear-ance, and motion. These synthesized observations are used to optimize 3D Gaussian primitives, which are then animated through a lightweight deformation module to form a 4D representation. The resulting scenes preserve geometry more faithfully, maintain smoother temporal behavior, and keep background edits more consistent, reducing context ambiguity and motion artifacts. Experiments on Objaverse-XL and Diffusion4D show that MATE4D outperforms strong baselines in visual quality, effi-ciency, and controllability, supporting practical AR/VR content creation.

Thu 8 OctComputer Vision and Pattern Recognition
The gist
Creating moving 3D scenes from just one photo is tricky because one picture doesn’t show all angles or movements clearly. The authors developed MATE4D, a method that turns a single image into a 4D (3D plus motion) model that you can change. It uses a matrix of images generated with text instructions to help learn how objects look, move, and appear from different views. Their system keeps the shapes accurate, movements smooth, and backgrounds consistent. This helps make dynamic virtual scenes that can be used in augmented and virtual reality.
Open → 2610.11181v1

Style transfer method reduces content leakage while keeping style intact

CLeaR: A Unified Framework for Resolving the Leakage-Degradation Dilemma in Style Transfer

Abstract: Style transfer aims to render target content in the style of a reference image, but existing methods often suffer from content leakage, where objects, layouts, or semantics from the style reference appear in the generated output. Although prior data-driven and training-free methods can reduce leakage, they often face a leakage-degradation dilemma: stronger content suppression may weaken style fidelity, while richer style preservation may reintroduce unwanted reference content. We identify this dilemma across the full style-transfer pipeline, including feature separation, feature-space grounding, and diffusion generation. To address these issues, we propose CLeaR, a training-free framework for content-leakage-resistant style transfer. CLeaR first uses Orthogonal Subspace Projection to define content-reduced style targets in each vision foundation model (VFM) feature space. It then performs Ensemble Inversion, which optimizes a shared pixel-space style anchor satisfying style constraints across multiple VFMs. Finally, Energy-Guided Calibration maintains style alignment during diffusion sampling by steering the denoising trajectory toward the ensemble-defined style manifold. We further provide a theoretical analysis showing that the style-anchor estimation error decreases with the number of VFMs. Experiments on StyleBench demonstrate that CLeaR improves style alignment, reduces content leakage, and achieves better LLM-as-Judge evaluation compared with existing methods. The code is available at \href{https://github.com/0606zt/CLeaR}{https://github.com/0606zt/CLeaR}.

Tue 29 SeptComputer Vision and Pattern Recognition
The gist
Style transfer tries to make a picture look like it's painted in the style of another image, but often bits of the original picture sneak through, making the final image look messy. The authors found that pushing too hard to remove these bits often ruins the style, and trying to keep the style strong brings back unwanted content. They created a new method called CLeaR that balances this by carefully separating content and style using multiple image analysis tools without extra training. This approach results in better style matching and less leakage in the generated images.
Open → 2609.38136v1

SafeStyle improves style transfer while avoiding content leaks

SafeStyle: Calibrated Style Residual Injection for Controllable Style-Leakage Trade-off in Diffusion Stylization

Abstract: Reference-guided diffusion stylization aims to transfer visual style from a reference image while preserving the semantics specified by a text prompt. However, image conditioning often entangles transferable style cues with reference-specific content, leading to an inherent trade-off: stronger conditioning improves style fidelity but increases content leakage, whereas aggressive suppression reduces leakage at the cost of style expression. This challenge is further complicated by the distinct spatial organization of texture- and geometry-dominant styles. To address these issues, we propose SafeStyle, a training-free framework for calibrated style residual injection in frozen diffusion models. SafeStyle first estimates style-supported and content-associated subspaces from compact calibration sets, preserving their informative overlap while suppressing useless content variations. It then transports the purified style evidence over adaptive spatial granularity and constrains its effective influence through an explicit residual-norm budget. Experiments across texture- and geometry-dominant styles show that SafeStyle achieves a DINO style similarity of 0.432 while maintaining competitive text alignment. On a semantically disjoint leakage-stress benchmark, it further achieves a DINO style similarity of 0.474 with only 0.8\% semantic leakage, demonstrating an effective balance between style fidelity and reference-content suppression.

Fri 18 SeptComputer Vision and Pattern Recognition
The gist
When changing a picture’s style using another image and text instructions, it’s hard to keep the new style without accidentally copying parts of the original picture. The authors developed SafeStyle, a method that carefully adds style details without letting unwanted original content leak through. It works without extra training, by separating and controlling style and content information to find a better balance. Tests show that SafeStyle keeps style strong while reducing accidental content copying.
Open → 2609.21242v1

Vehicle shape and size recovered from limited images using priors

Leveraging Visual and Geometric Priors for Metric-scale and Complete Vehicle Gaussian Reconstruction from Limited Views

Abstract: High-fidelity vehicle assets are essential for controllable traffic scene generation, particularly for synthesizing rare and safety-critical long-tail scenarios. However, reconstructing a reusable vehicle representation from in-the-wild onboard images remains challenging for two reasons. First, image-to-3D generation methods generally produce models without reliable metric scale. Second, onboard cameras usually observe only one side of a target vehicle, making conventional multi-view reconstruction incomplete on unobserved regions. To solve these problems, we propose a feed-forward vehicle asset reconstruction method, which leverages two complementary priors to reconstruct 3D Gaussian representations for vehicles using sparse one-sided observations. To achieve metric-scale reconstruction, a visual foundation model is first utilized to serve as a visual prior for Gaussian initialization. The Gaussian attributes are then estimated by a learnable encoder-decoder module. A symmetry-aware cloning strategy is presented to complete the unobserved side directly in Gaussian space, which exploits the bilateral structure of vehicles as a geometric prior. Experiments on the public dataset demonstrate that the proposed method significantly outperforms existing approaches in both vehicle asset completeness and geometric accuracy.

Tue 8 SeptComputer Vision and Pattern Recognition
The gist
It is difficult to create accurate 3D models of vehicles from just a few photos taken from one side because the scale is unclear and the other side is missing. The authors use visual clues from a foundation model to start the shape and size, then apply a special method that copies the seen side to the unseen side, since most vehicles are symmetrical. This approach makes it possible to build a complete and correctly sized 3D vehicle model even from just one viewpoint. Their tests show this method works better than others in creating full and precise vehicle shapes.
Open → 2609.08841v1