Computer Graphics Forum
Publisher: Wiley · ISSN 01677055 · 15 articles
-
Telligram: Text‐Driven Calligram Generation via Diffusion‐Guided Skeleton Optimization
Abstract Compact calligram generation aims to form a semantic shape while keeping letters recognizable. Most existing methods are shape‐conditioned and mainly solve downstream letter layout inside a given contour. We study text‐only...
-
Curvature‐matched 5‐axis CNC machining using non‐circular toroidal cutters
Abstract Highly accurate 5‐axis CNC machining requires a good, ideally higher order, match between the cutting tool and the reference surface along a common tangent direction. It has been shown that one can apply this, so‐called...
-
A Survey of Modelling Temporal Coherence in Neural Rendering and Video Generation
Abstract With the recent surge in generative AI video models and neural rendering techniques, a key quality factor is the (spatio‐)temporal consistency of the generated or rendered sequence over its duration. Classic rendering methods,...
-
Reliability‐Aware Adaptive Gaussian Propagation for Low‐Texture Dynamic Outdoor Scenes
Abstract 3D Gaussian Splatting (3DGS) remains challenging in dynamic outdoor scenes where dynamic distractors are coupled with large low‐texture regions such as roads and walls. Binary mask‐based foreground removal is...
-
Image Vectorization with Generalized Coons Patches
Abstract Patch‐based image vectorization methods usually represent image regions using fixed‐sided patches, such as triangular or quadrilateral patches. However, such patches are often inefficient for irregular or semantically complex...
-
OrnaStyler : Ornament‐Aware Latent Editing for Content‐Preserving 3D Stylization
Abstract Text‐guided style editing of 3D assets is essential for adapting existing objects to diverse visual aesthetics in digital content creation. Despite rapid progress in 3D shape modeling, faithfully stylizing an existing asset...
-
Camera Splatting for Continuous View Optimization
Abstract Given limited camera budgets, identifying informative views is essential for effectively reconstructing a radiance field to achieve high‐quality novel view synthesis. These views should adaptively sample the radiance field...
-
Dream4D: Lifting Camera‐Controlled I2V towards Spatiotemporally Consistent 4D Generation
Abstract Generating spatiotemporally consistent 4D content requires joint modeling of high‐fidelity spatial details and realistic temporal dynamics. However, existing methods typically lack world knowledge learned from expansive 4D...
-
Scalable Capacity‐Constrained Power Diagrams via Compressed Optimal Assignment
Abstract Power diagrams with prescribed capacities are widely used in geometry processing, including blue‐noise sampling, remeshing, and constrained clustering. The problem can be viewed as a semi‐discrete optimal transport problem and...
-
Implicit Surface Tension for Incompressible SPH Fluids with Interface Classification
Abstract In computer graphics and physics‐based animation, surface tension is an important factor in reproducing small‐scale fluid features. However, existing surface tension solvers often incur high computational costs and tend to...
-
MGAvatar: Mesh‐Bound Gaussians for Head Avatar Geometry and Appearance Modeling
Abstract Accurate head modeling requires a stable yet expressive geometric representation. Existing Gaussian‐based head avatars commonly rely on parametric templates (e.g., FLAME) for Gaussian initialization and deformation, but these...
-
FlySeek: Visibility‐Aware Viewpoint Planning for Adversarial Target Pursuit in Complex 3D Scenes
Abstract Maintaining visual contact with moving targets in complex three‐dimensional environments is a fundamental challenge for aerial visual computing, as target visibility is jointly affected by scene geometry, dynamic motion, and...
-
Bijective Shape Correspondence through Nonlinear Spectral Embedding Alignment
Abstract Bijective correspondence is essential for texture and signal transfer, serving as a core benchmark for shape matching quality. Although the recently proposed Neural Adjoint Map (NAM) advances 3D shape correspondence by...
-
Q‐MAGIC: Quad‐only Mesh Autoregressive Generation via Singularity‐Aware Circular Relative Offset Tokenization
Abstract Autoregressive models have proven effective for triangular mesh generation by transforming it into predicting the next face, converting the non‐differentiable connectivity prediction into a sequence of token predictions....
-
EvoGS: Modeling Deformation Evolution for Dynamic Gaussian Splatting
Abstract Recent extensions of 3D Gaussian Splatting (3DGS) enable real‐time novel view synthesis in dynamic scenes by learning time‐conditioned Gaussian deformations. However, existing MLP‐based methods typically estimate deformations...