43-Issue 2
Browse by
Shape and Scene Understanding
Neural Semantic Surface Maps
] [
]
HaLo-NeRF: Learning Geometry-Guided Semantics for Exploring Unconstrained Photo Collections
Raster-to-Graph: Floorplan Recognition via Autoregressive Graph Prediction with an
Attention Transformer
Reflectance and Shading Models
Interactive Exploration of Vivid Material Iridescence based on Bragg Mirrors
Single-Image SVBRDF Estimation with Learned Gradient Descent
Procedural Modeling and Architectural Design
PossibleImpossibles: Exploratory Procedural Design of Impossible Structures
Hierarchical Co-generation of Parcels and Streets in Urban Modeling
Strokes2Surface: Recovering Curve Networks From 4D Architectural Design Sketches
Real-time Neural Rendering
TRIPS: Trilinear Point Splatting for Real-Time Radiance Field Rendering
Real-time Neural Rendering of Dynamic Light Fields
Real-Time Neural Materials using Block-Compressed Features
Neural 3D Shape Synthesis
SENS: Part-Aware Sketch-based Implicit Neural Shape Modeling
Physically-Based Lighting for 3D Generative Models of Cars
Rendering Natural Phenomena
Real-Time Underwater Spectral Rendering
Physically Based Real-Time Rendering of Atmospheres using Mie Theory
An Empirically Derived Adjustable Model for Particle Size Distributions in Advection Fog
Geometry Processing
BallMerge: High-quality Fast Surface Reconstruction via Voronoi Balls
Non-Euclidean Sliced Optimal Transport Sampling
GLS-PIA: n-Dimensional Spherical B-Spline Curve Fitting based on Geodesic Least Square with
Adaptive Knot Placement
Cloth Simulation
Estimating Cloth Simulation Parameters From Tag Information and Cusick Drape Test
Neural Garment Dynamics via Manifold-Aware Transformers
Practical Method to Estimate Fabric Mechanics from Metadata
Meshes
Polygon Laplacian Made Robust
Advancing Front Surface Mapping
Fluid Simulation
The Impulse Particle-In-Cell Method
Wavelet Potentials: An Efficient Potential Recovery Technique for Pointwise Incompressible
Fluids
Monte Carlo Vortical Smoothed Particle Hydrodynamics for Simulating Turbulent Flows
Fabrication
Computational Smocking through Fabric-Thread Interaction
Unfolding via Mesh Approximation using Surface Flows
Freeform Shape Fabrication by Kerfing Stiff Materials
Simulating Natural Phenomena
Physically-based Analytical Erosion for fast Terrain Generation
Volcanic Skies: Coupling Explosive Eruptions with Atmospheric Simulation to Create
Consistent Skyscapes
Perceptual Rendering
Navigating the Manifold of Translucent Appearance
Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front-Facing
Views
Predicting Perceived Gloss: Do Weak Labels Suffice?
Digital Humans and Characters
TailorMe: Self-Supervised Learning of an Anatomically Constrained Volumetric Human Shape
Model
CharacterMixer: Rig-Aware Interpolation of 3D Characters
Stylize My Wrinkles: Bridging the Gap from Simulation to Reality
Sampling and Image Enhancement
Enhancing Image Quality Prediction with Self-supervised Visual Masking
Enhancing Spatiotemporal Resampling with a Novel MIS Weight
Neural Denoising for Deep-Z Monte Carlo Renderings
Face Modeling and Reconstruction
Learning to Stabilize Faces
3D Reconstruction and Semantic Modeling of Eyelashes
ShellNeRF: Learning a Controllable High-resolution Model of the Eye and Periocular Region
Vector Art and Line Drawings
Region-Aware Simplification and Stylization of 3D Line Drawings
Vector Art and Line Drawings
FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications
Sketch Video Synthesis
Neural Texture and Image Synthesis
Surface-aware Mesh Texture Synthesis with Pre-trained 2D CNNs
GANtlitz: Ultra High Resolution Generative Model for Multi-Modal Face Textures
Stylized Face Sketch Extraction via Generative Prior with Limited Data
Camera Paths and Motion Tracking
Cinematographic Camera Diffusion Model
OptFlowCam: A 3D-Image-Flow-Based Metric in Camera Space for Camera Paths in Scenes with
Extreme Scale Variations
DivaTrack: Diverse Bodies and Motions from Acceleration-Enhanced 3-Point Trackers
Recent Submissions
-
DivaTrack: Diverse Bodies and Motions from Acceleration-Enhanced 3-Point Trackers
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Full-body avatar presence is important for immersive social and environmental interactions in digital reality. However, current devices only provide three six degrees of freedom (DOF) poses from the headset and two controllers ... -
OptFlowCam: A 3D-Image-Flow-Based Metric in Camera Space for Camera Paths in Scenes with Extreme Scale Variations
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Interpolation between camera positions is a standard problem in computer graphics and can be considered the foundation of camera path planning. As the basis for a new interpolation method, we introduce a new Riemannian ... -
Cinematographic Camera Diffusion Model
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Designing effective camera trajectories in virtual 3D environments is a challenging task even for experienced animators. Despite an elaborate film grammar, forged through years of experience, that enables the specification ... -
Stylized Face Sketch Extraction via Generative Prior with Limited Data
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Facial sketches are both a concise way of showing the identity of a person and a means to express artistic intention. While a few techniques have recently emerged that allow sketches to be extracted in different styles, ... -
GANtlitz: Ultra High Resolution Generative Model for Multi-Modal Face Textures
(The Eurographics Association and John Wiley & Sons Ltd., 2024)High-resolution texture maps are essential to render photoreal digital humans for visual effects or to generate data for machine learning. The acquisition of high resolution assets at scale is cumbersome, it involves ... -
Surface-aware Mesh Texture Synthesis with Pre-trained 2D CNNs
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Mesh texture synthesis is a key component in the automatic generation of 3D content. Existing learning-based methods have drawbacks-either by disregarding the shape manifold during texture generation or by requiring a large ... -
FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Acquiring the desired font for various design tasks can be challenging and requires professional typographic knowledge. While previous font retrieval or generation works have alleviated some of these difficulties, they ... -
Sketch Video Synthesis
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Understanding semantic intricacies and high-level concepts is essential in image sketch generation, and this challenge becomes even more formidable when applied to the domain of videos. To address this, we propose a novel ... -
Region-Aware Simplification and Stylization of 3D Line Drawings
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Shape-conveying line drawings generated from 3D models normally create closed regions in image space. These lines and regions can be stylized to mimic various artistic styles, but for complex objects, the extracted topology ... -
ShellNeRF: Learning a Controllable High-resolution Model of the Eye and Periocular Region
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Eye gaze and expressions are crucial non-verbal signals in face-to-face communication. Visual effects and telepresence demand significant improvements in personalized tracking, animation, and synthesis of the eye region ... -
3D Reconstruction and Semantic Modeling of Eyelashes
(The Eurographics Association and John Wiley & Sons Ltd., 2024)High-fidelity digital human modeling has become crucial in various applications, including gaming, visual effects and virtual reality. Despite the significant impact of eyelashes on facial aesthetics, their reconstruction ... -
Learning to Stabilize Faces
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Nowadays, it is possible to scan faces and automatically register them with high quality. However, the resulting face meshes often need further processing: we need to stabilize them to remove unwanted head movement. ... -
Neural Denoising for Deep-Z Monte Carlo Renderings
(The Eurographics Association and John Wiley & Sons Ltd., 2024)We present a kernel-predicting neural denoising method for path-traced deep-Z images that facilitates their usage in animation and visual effects production. Deep-Z images provide enhanced flexibility during compositing ... -
Enhancing Spatiotemporal Resampling with a Novel MIS Weight
(The Eurographics Association and John Wiley & Sons Ltd., 2024)In real-time rendering, optimizing the sampling of large-scale candidates is crucial. The spatiotemporal reservoir resampling (ReSTIR) method provides an effective approach for handling large candidate samples, while the ... -
Enhancing Image Quality Prediction with Self-supervised Visual Masking
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Full-reference image quality metrics (FR-IQMs) aim to measure the visual differences between a pair of reference and distorted images, with the goal of accurately predicting human judgments. However, existing FR-IQMs, ... -
Stylize My Wrinkles: Bridging the Gap from Simulation to Reality
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Modeling realistic human skin with pores and wrinkles down to the milli- and micrometer resolution is a challenging task. Prior work showed that such micro geometry can be efficiently generated through simulation methods, ... -
CharacterMixer: Rig-Aware Interpolation of 3D Characters
(The Eurographics Association and John Wiley & Sons Ltd., 2024)We present CharacterMixer, a system for blending two rigged 3D characters with different mesh and skeleton topologies while maintaining a rig throughout interpolation. CharacterMixer also enables interpolation during motion ... -
TailorMe: Self-Supervised Learning of an Anatomically Constrained Volumetric Human Shape Model
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Human shape spaces have been extensively studied, as they are a core element of human shape and pose inference tasks. Classic methods for creating a human shape model register a surface template mesh to a database of 3D ... -
Predicting Perceived Gloss: Do Weak Labels Suffice?
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Estimating perceptual attributes of materials directly from images is a challenging task due to their complex, not fullyunderstood interactions with external factors, such as geometry and lighting. Supervised deep learning ... -
Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front-Facing Views
(The Eurographics Association and John Wiley & Sons Ltd., 2024)Neural view synthesis (NVS) is one of the most successful techniques for synthesizing free viewpoint videos, capable of achieving high fidelity from only a sparse set of captured images. This success has led to many variants ...
RSS 1.0