ACM Trans. Graphics 2018

201 papers
In 2018, ACM Transactions on Graphics featured research centered on the development of digital humans and high-fidelity avatars. Key themes included expressive whole-body animation and the creation of human models that move beyond standard parametric templates. Notable work in this area, such as the paper LookinGood, focused on enhancing the realism and fidelity of digital representations. Other significant research directions involved computational fabrication and material modeling, represented by papers such as FlexMaps, Metamolds, and CoreCavity. The year also saw an integration of machine learning techniques for graphics tasks, including efficient reflectance capture via autoencoders and interactive aerodynamic design through three-dimensional flow learning. Prolific contributors to the volume included Bernd Bickel, Matthias Nießner, Michael Zollhöfer, and Paolo Cignoni, reflecting a broad interest in geometry processing, physical simulation, and appearance modeling.

Top Research Directions

Research directions most represented by ACM Trans. Graphics 2018 papers.

Aligning Generative Media with Human Perceptual Preferences 2
Preventing Mesh Self Intersection and Element Inversion 2
Physics Constrained Generative Human Motion Synthesis 2
Reconstructing Thin Structures in 3D Geometry 2
Support-Free Fabrication via Multi-Axis Additive Manufacturing 1
Traveling Salesman Formulations for Autonomous Path Planning 1
Perceptual Quality Assessment Under Variable Viewing Conditions 1
Directional Information Loss in Rotation Invariant Networks 1
Sparse Spectral Discretization of Differential Operators 1
Learning Geometric Representations Directly from Raw 3D Data 1
Neural Sequence Embeddings for Fast Similarity Search 1
High Frequency Geometric Complexity in 3D Hair Modeling 1
Overcoming Geometric Discretization Error in High-Order Methods 1
Numerical Methods for Non-Smooth Interfaces and Boundaries 1
High-Dimensional Optimization via One-Dimensional Reduction 1

Top Authors

AuthorPapers
Daniel Cohen-Or10
Hui Huang10
Christian Theobalt6
Xin Tong6
Bernd Bickel5
Hao Richard Zhang5
Ravi Ramamoorthi5
Sean Fanello5
Wolfgang Heidrich5
Changxi Zheng4
Dani Lischinski4
Dinesh Manocha4
Jing Liao4
Justin Solomon4
Michael Zollhöfer4
Niloy Mitra4
Peter Wonka4
Ruizhen Hu4
Wenping Wang4
Wojciech Matusik4

Impactful Papers

Papers from ACM Trans. Graphics 2018 that shaped research clusters.

Foundational

Influential

Papers

Title
InverseCSG: automatic conversion of 3D models to CSG trees
InverseCSG: automatic conversion of 3D models to CSG trees.
Invertible grayscale
Iterative Depth Warping
Language-driven synthesis of 3D scenes from scene databases
Laplacian kernel splatting for efficient depth-of-field and motion blur synthesis or reconstruction
Layered fields for natural tessellations on surfaces
Learning a shared shape space for multimodal garment design
Learning basketball dribbling skills using trajectory optimization and deep reinforcement learning
Learning Local Shape Descriptors from Part Correspondences with Multiview Convolutional Networks
Learning symmetric and low-energy locomotion
Learning three-dimensional flow for interactive aerodynamic design
Learning to dress: synthesizing human dressing motion via deep reinforcement learning
Learning to group and label fine-grained shape components
Learning to reconstruct shape and spatially-varying reflectance from a single image
Light in power: a general and parameter-free algorithm for caustic design
Locally Adaptive Rank-Constrained Optimal Tone Mapping
LookinGood: enhancing performance capture with real-time neural re-rendering
Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation
Manipulating Attributes of Natural Scenes via Hallucination
Mean value coordinates for quad cages in 3D
Mechanical characterization of structured sheet materials
Megapixel adaptive optics: towards correcting large-scale distortions in computational cameras
MeshCNN: A Network with an Edge
Metamolds
Mode-adaptive neural networks for quadruped motion control
Modeling hair from an RGB-D camera
Modeling n-Symmetry Vector Fields using Higher-Order Energies
MonoPerfCap: Human Performance Capture From Monocular Video
Monte Carlo convolution for learning on non-uniformly sampled point clouds
Multi-chart generative surface modeling
Multi-directional geodesic neural networks via equivariant convolution
Multi-scale simulation of nonlinear thin-shell sound with wave turbulence
Multi-view wire art
Narrow-band topology optimization on a sparsely populated grid
Natural Boundary Conditions for Smoothing in Geometry Processing
Neural best-buddies: sparse cross-domain correspondence
Non-Stationary Texture Synthesis by Adversarial Expansion
Numerical coarsening using discontinuous shape functions
Object-aware guidance for autonomous scene reconstruction
OptCuts: joint optimization of surface cuts and parameterization
Optimizing for aesthetically pleasing qadrotor camera motion
P2P-NET: bidirectional point displacement net for shape transform
paGAN: real-time avatars using dynamic textures
Paparazzi: surface editing by way of multi-view image processing
Perception-aware modeling and fabrication of digital drawing tools
PhotoShape: photorealistic materials for large-scale shape collections
Physics-Inspired Garment Recovery from a Single-View Image
Point convolutional neural networks by extension operators
Portrait Lighting Transfer Using a Mass Transport Approach

« prev Page 3/5 next »