SIGGRAPH-2022-Asia.md

SIGGRAPH ASIA 2022

Simulation/Animation

• A Biologically Inspired Hair Aging Model

• Interactive Exploration of Tension-compression Mixed Shells(Mechanics) 力学

Real-Time Simulation

• Differentiable Hybrid Traffic Simulation code

• Fluidic Topology Optimization with an Anisotropic Mixture Model

• Differentiable Simulation of Inertial Musculotendons

• A Monte Carlo Method for Fluid Simulation(Modeling and simulation)

• ElastoMonolith: A Monolithic Optimization-based Liquid Solver for Contact-Aware Elastic-Solid Coupling(基于物理的仿真)

• Curl-Flow: Pointwise Incompressible Velocity Interpolation for Grid-Based Fluids

• Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly

• Position-based Surface Tension Flow

• Progressive Simulation for Cloth Quasistatics

• Simulation of Hand Anatomy Using Medical Imaging

• Fast Stabilization of Inducible Magnet Simulation

Physics-Based Animation

Garments

• Motion Guided Deep Dynamic 3D Garments code

• Physical Interaction: Reconstructing Hand-object Interactions with Physics

Reinforcement learning

• ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characters

Physically-based simulation

• Breaking Good: Fracture Modes for Realtime Destruction code

• ElastoMonolith: A Monolithic Optimization-based Liquid Solver for Contact-Aware Elastic-Solid Coupling

Rendering

• Differentiable rendering using RGBXY derivatives and optimal transport
• Look-Ahead Training with Learned Reflectance Loss for Single-Image SVBRDF Estimation
• Efficient Differentiation of Pixel Reconstruction Filters for Path-Space Differentiable Rendering
• Neural Parameterization for Dynamic Human Head Editing

Reflectance modeling

• Affordable Spectral Measurements of Translucent Materials

• QuadStream: A Quad-Based Scene Streaming Architecture for Novel Viewpoint Reconstruction

• Differentiable Rendering of Neural SDFs through Reparameterization

• Lightweight Neural Basis Functions for All-Frequency Shading

Ray Tracing

• Neural James-Stein Combiner for Unbiased and Biased Renderings

• Scalable multi-class sampling via filtered sliced optimal transport

• Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing

• Marginal Multiple Importance Sampling

• Unbiased Caustics Rendering Guided by Representative Specular Paths

View synthesis

• Neural Point Catacaustics for Novel-View Synthesis of Reflection
• Differentiable Point-Based Radiance Fields for Efficient View Synthesis
• VIINTER: View Interpolation with Implicit Neural Representations of Image

Light Transport

• Metappearance: Meta-Learning for Visual Appearance Reproduction

Reflectance modeling.

• Woven Fabric Capture from a Single Photo

Non-photorealistic rendering

• AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging

Image-based rendering

• Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing

• Water Simulation and Rendering from a Still Photograph

• Fast Dynamic Radiance Fields with Time-Aware Neural Voxels code video

Texture representations

• Gloss management for consistent reproduction of real and virtual objects

COMPUTER VISION

IMAGE PROCESSING

• MyStyle: A Personalized Generative Prior

• DISCO: Disentangled Image Colorization via Global Anchors AI,图像着色

• NeuralMarker: A Framework for Learning General Marker Correspondence

• DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains

• [Dr.3D: Adapting 3D GANs to Artistic Drawings] code

• Shape Completion with Points in the Shadow

IMAGE manipulation

• Production-Ready Face Re-Aging for Visual Effects
• Pivotal Tuning for Latent-based Editing of Real Images
• UniColor: A Unified Framework for Multi-Modal Colorization with Transformer

GEOMTERY MODELING AND PROCESSING

• Computing Medial Axis Transform with Feature Preservation via Restricted Power Diagram
• NH-Rep: Neural Halfspace Representations for Implicit Conversion of B-Rep Solids (THU)
• Globally Injective Flattening via a Reduced Harmonic Subspace

Point sampling

• Gaussian Blue Noise

Mesh geometry models

• CLIP-Mesh: Generating textured meshes from text using pretrained image-text models
• Fast Editing of Singularities in Field-Aligned Stripe Patterns

Shape inference

• Rapid Face Asset Acquisition with Recurrent Feature Alignment

Shape analysis

• Augmented Paths and Reodesics for Topologically-Stable Matching
• Neural Wavelet-domain Diffusion for 3D Shape Generation

Shape modeling; Shape representations.

• An Implicit Parametric Morphable Dental Model

• Exact 3D Path Generation via 3D Cam-Linkage Mechanisms

• Planar panels and planar supporting beams in architectural structures

• Declarative Specification for Unstructured Mesh Editing Algorithms code

• DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repair

CAD

• [Reconstructing editable prismatic CAD from rounded voxel models]

• CAD2Sketch: Generating Concept Sketches from CAD Sequences

RECONSTRUCTING

• Reconstructing Personalized Semantic Facial NeRF Models From Monocular Video 3D重建 NeRF(ECCV) 广泛应用

• Stochastic Poisson Surface Reconstruction

• 3QNet: 3D Point Cloud Geometry Quantization Compression Network

• LaplacianFusion: Detailed 3D Clothed-Human Body Reconstruction

• Asynchronous Collaborative Autoscanning with Mode Switching for Multi-Robot Scene Reconstruction

• [NeuralRoom: Geometry-Constrained Neural Implicit Surfaces for Indoor Scene Reconstruction}(https://arxiv.org/pdf/2210.06853.pdf)

• FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editing

TOOLS

Mesh Tools

• Interactive and Robust Mesh Booleans code
• Make Your Own Sprites: Aliasing-Aware and Cell-Controllable Pixelization

APPLICATION

• Affordable Spectral Measurements of Translucent Materials

• Motion In-betweening via Two-stage Transformers 生成目标帧

• Scene Synthesis from Human Motion

• Pupil-aware Holography

• Neural Photo-Finishing (CV+AI)

• TileGen: Tileable, Controllable Material Generation and Capture(GAN,TILE)

• Color-Perception-Guided Display Power Reduction for Virtual Reality VR设备省电

• Garment Avatars: Realistic Cloth Driving using Pattern Registration

• Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings

• SCULPTOR: Skeleton-Consistent Face Creation Using a Learned Parametric Generator

• Text2Light: Zero-Shot Text-Driven HDR Panorama Generation code

• NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fields

• Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers

Video Style Transfer

• VToonify: Controllable High-Resolution Portrait Video Style Transfer

Video Editing

• VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
• Stitch it in Time: GAN-Based Facial Editing of Real Videos

Hair Modeling

• DeepMVSHair: Deep Hair Modeling from Sparse Views

VR,MR,HCI

• Force-Aware Interface via Electromyography for Natural VR/AR Interaction

• Realistic Luminance in VR

Motion capture

• QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars
• Video-driven Neural Physically-based Facial Asset for Production
• Transformer Inertial Poser: Real-time Human Motion Reconstruction from Sparse IMUs with Simultaneous Terrain
• Morig: Motion-aware rigging of character meshes from point clouds

Graphics systems and interfaces

• DifferSketching: How Differently Do People Sketch 3D Objects? code

• Neural Brushstroke Engine: Learning a Latent Style Space of Interactive Drawing Tools

GAMES

• Sprite-from-Sprite: Cartoon Animation Decomposition with Self-supervised Sprite Estimation 将Sprite进行解构

[Reference]

• 大规模网格模型间的快速视觉布尔运算