ACM Trans. Graphics

3,373 papers745 directions
ACM Transactions on Graphics (TOG) is an established publication venue for research at the intersection of computer graphics, computer vision, and machine learning. Active since 2002, the venue features work focused on the synthesis, modeling, and reconstruction of complex visual and physical data. Within the machine learning community, it is recognized for its contributions to generative modeling for human motion, 3D animation, and digital human representation. Research frequently addresses technical challenges such as aligning generative motion with human perception, bridging data gaps in 3D motion, and developing unified frameworks for expression and gesture generation. The venue's recent publications highlight an increasing integration of deep learning architectures, including diffusion models and multimodal transformers. Specific research directions include text-guided garment generation, training-free image editing frameworks, and high-fidelity avatar creation that extends beyond standard parametric templates. Prolific contributors to the venue include researchers such as Bernd Bickel, Wojciech Matusik, Kun Zhou, and Matthias Nießner. By hosting work on topics like semantic alignment in gesture synthesis and robust skinning using geometric fields, the venue serves as a bridge between traditional geometric modeling and modern neural-based synthesis methods.

Papers by Year

2026 96
2025 177
2024 188
2023 182
2022 189
2021 213
2020 173
2019 174
2018 201
2017 179
2016 176
2015 176
2014 174
2013 151
2012 136
2011 123
2010 130
2009 122
2008 110
2007 83
2006 63
2005 60
2004 50
2003 47
2002 28
2001 3
2000 2
1999 4
1998 3
1997 3
1996 1
1995 2
1994 3
1993 2
1992 2
1990 2
1989 2
1988 1
1987 1
1986 1
1985 1
1984 3
1982 1

Top Research Directions

Research directions most represented by papers from this venue.

Generative Simulation for Scaling Embodied AI 28
Physics Constrained Generative Human Motion Synthesis 13
Aligning Generative Media with Human Perceptual Preferences 12
Hybrid Representations for High-Fidelity 3D Reconstruction 11
Resolving Mesh Interpenetration in Neural Garment Simulation 8
Mask-Free Local Image Editing in Generative Models 8
Composite Loss Functions for Perceptual Image Restoration 8
Generative Hallucination for Disoccluded Region Synthesis 8
Material Lighting Disentanglement for 3D Reconstruction 8
Preventing Mesh Self Intersection and Element Inversion 7
Untethering 3D Motion Capture from Studio Infrastructure 7
Backpropagating Through Physical Laws for System Identification 7
Overcoming the Fixed Topology Constraint in 3D Modeling 7
Accelerating Neural Scene Representations for Real Time Rendering 7
Reconstructing Complete Geometry from Partial Point Clouds 7

Top Authors

AuthorPapers
Daniel Cohen-Or145
Ravi Ramamoorthi90
Wojciech Matusik86
Niloy Mitra83
Christian Theobalt68
Xin Tong64
Hans-peter Seidel60
Hui Huang60
Hao Richard Zhang57
Fredo Durand56
Ligang Liu56
Wenping Wang53
Bernd Bickel48
Jessica K. Hodgins48
Hujun Bao47
Ariel Shamir43
Gordon Wetzstein43
Wolfgang Heidrich40
Dani Lischinski38
Leonidas Guibas38

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Photo-to-shape material transfer for diverse structures2022
Physics-based character controllers using conditional VAEs2022
Physics informed neural fields for smoke reconstruction with sparse data2022
Position-Based Surface Tension Flow2022
Position-free multiple-bounce computations for smith microfacet BSDFs2022
Procedural Urban Forestry2022
Production-Ready Face Re-Aging for Visual Effects2022
Pupil-Aware Holography2022
QuadStream: A Quad-Based Scene Streaming Architecture for Novel Viewpoint Reconstruction2022
R2E2: low-latency path tracing of terabyte-scale scenes using thousands of cloud CPUs2022
Rapid Face Asset Acquisition with Recurrent Feature Alignment2022
Real-time Controllable Motion Transition for Characters2022
Restricted Delaunay Triangulation for Explicit Surface Reconstruction2022
Rewriting geometric rules of a GAN2022
RFEPS: Reconstructing Feature-Line Equipped Polygonal Surface2022
Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings2022
Scalable Multi-Class Sampling via Filtered Sliced Optimal Transport2022
Scalable neural indoor scene rendering2022
SCULPTOR: Skeleton-Consistent Face Creation Using a Learned Parametric Generator2022
Seeing through obstructions with diffractive cloaking2022
Semantically supervised appearance decomposition for virtual staging from a single panorama2022
SGN: Sparse Gauss-Newton for Accelerated Sensitivity Analysis2022
Shape from Release: Inverse Design and Fabrication of Controlled Release Structures2022
SHRED: 3D Shape Region Decomposition with Learned Local Operations2022
Simulating Brittle Fracture with Material Points2022
Simulation and optimization of magnetoelastic thin shells2022
Simulation of Hand Anatomy Using Medical Imaging2022
Sketch2Pose: estimating a 3D character pose from a bitmap sketch2022
SNeRF: stylized neural implicit representations for 3D scenes2022
SofGAN: A Portrait Image Generator with Dynamic Styling2022
SPAGHETTI: editing implicit shapes through part aware generation2022
Sparse ellipsometry: portable acquisition of polarimetric SVBRDF and shape with unstructured flash photography2022
Sparsity-Specific Code Optimization using Expression Trees2022
Sprite-from-Sprite: Cartoon Animation Decomposition with Self-supervised Sprite Estimation2022
Stochastic Poisson Surface Reconstruction2022
StyleFusion: Disentangling Spatial Segments in StyleGAN-Generated Images2022
StyleGAN-NADA: CLIP-guided domain adaptation of image generators2022
Subdivision-based Mesh Convolution Networks2022
SurfaceVoronoi: Efficiently Computing Voronoi Diagrams over Mesh Surfaces with Arbitrary Distance Solvers2022
Synthesis of Frame Field-Aligned Multi-Laminar Structures2022
Text2Human: text-driven controllable human image generation2022
Text2Light: Zero-Shot Text-Driven HDR Panorama Generation2022
TextureMe: High-Quality Textured Scene Reconstruction in Real Time2022
The power particle-in-cell method2022
TightCap: 3D Human Shape Capture with Clothing Tightness Field2022
TopoCut: fast and robust planar cutting of arbitrary domains2022
Umbrella meshes: elastic mechanisms for freeform shape deployment2022
UniColor: A Unified Framework for Multi-Modal Colorization with Transformer2022
VEMPIC: particle-in-polyhedron fluid simulation for intricate solid boundaries2022
Video-Driven Neural Physically-Based Facial Asset for Production2022

« prev Page 16/68 next »