arXivSub Start free trial

SIGGRAPH Asia 2023 Papers with Code

ACM SIGGRAPH Asia (Transactions on Graphics) · 31 papers with a public code repository

A Locality-based Neural Solver for Optical Motion Capture

Xiaoyu Pan (Zhejiang University), Xiaogang Jin (Zhejiang University)

CodePose EstimationOptimizationRecurrent Neural NetworkGraph Neural NetworkAuto EncoderContrastive LearningOptical FlowPoint CloudGraphTime Series

🎯 What it does: Propose a method for cleaning and motion solving of optical motion capture data based on locality and heterogeneous graph neural networks.

CamP: Camera Preconditioning for Neural Radiance Fields

Keunhong Park (Google Research), Ricardo Martin-Brualla (Google Research)

CodeOptimizationComputational EfficiencyRepresentation LearningNeural Radiance FieldImagePoint Cloud

🎯 What it does: Propose and study the CamP camera preprocessing method, which aims to improve the joint optimization of camera parameters in NeRF, thereby enhancing the quality of 3D scene reconstruction.

Computational Design of Wiring Layout on Tight Suits with Minimal Motion Resistance

Kai Wang (Xiamen University), Xiaohu Guo (University of Texas at Dallas)

CodeOptimizationDiffusion modelOptical FlowVideoPoint CloudMesh

🎯 What it does: This paper proposes an automated method for cable layout design in tight-fitting clothing, aiming to minimize cable resistance during the wearer's movements.

Constrained Delaunay Tetrahedrization: A Robust and Practical Approach

Lorenzo Diazzi (UniMoRe), M. Attene

CodeOptimizationComputational EfficiencyRobotic IntelligenceDiffusion modelScore-based ModelAuto EncoderGenerative Adversarial NetworkContrastive LearningPoint CloudMeshBenchmark

🎯 What it does: Designed and implemented a numerically robust, parameter-independent 3D Constrained Delaunay Tetrahedralization (CDT) algorithm that can successfully construct CDT on all valid PLCs.

Content-based Search for Deep Generative Models

Daohan Lu (Carnegie Mellon University), Jun-Yan Zhu (Carnegie Mellon University)

CodeGenerationData SynthesisRetrievalRepresentation LearningTransformerVision Language ModelDiffusion modelScore-based ModelFlow-based ModelRectified FlowContrastive LearningImageTextMultimodalityBenchmarkAudio

🎯 What it does: This paper proposes a content-driven deep generative model retrieval task and constructs the Generative Model Zoo benchmark. It introduces a retrieval framework based on probabilistic and contrastive learning, which can retrieve text, images, sketches, and models themselves.

Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Input

Donglai Xiang (Carnegie Mellon University), Timur M. Bagautdinov

CodeGenerationData SynthesisPose EstimationDepth EstimationConvolutional Neural NetworkGraph Neural NetworkTransformerDiffusion modelNeural Radiance FieldAuto EncoderContrastive LearningOptical FlowImageVideoPoint CloudMesh

🎯 What it does: Constructed a full-body holographic avatar driven by sparse RGB-D input, capable of realistically reproducing the dynamics and details of loose clothing.

Efficient Graphics Representation with Differentiable Indirection

Sayantani Datta (McGill University), Derek Nowrouzezahrai (McGill University)

CodeCompressionComputational EfficiencyRepresentation LearningDiffusion modelNeural Radiance FieldAuto EncoderContrastive LearningImagePoint CloudMesh

🎯 What it does: Proposes a novel differentiable memory table primitive called Differentiable Indirection (DIn), which replaces MLP computations in traditional neural networks to achieve efficient representation and compression for various graphics tasks such as geometry, texture, shading, and radiance fields.

EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation

Zhengzhe Liu, Chi-Wing Fu

CodeGenerationData SynthesisTransformerVision Language ModelDiffusion modelNeural Radiance FieldAuto EncoderImageTextMesh

🎯 What it does: This paper proposes a hybrid explicit-implicit representation method called EXIM, which generates high-fidelity 3D shapes guided by text and supports local editing.

Explorable Mesh Deformation Subspaces from Unstructured 3D Generative Models

Arman Maesumi (Brown University), Daniel Ritchie (Brown University)

CodeGenerationData SynthesisDiffusion modelScore-based ModelFlow-based ModelGenerative Adversarial NetworkPoint CloudMesh

🎯 What it does: By constructing a two-dimensional navigable exploration space, the high-dimensional latent space of a pre-trained 3D shape generation model is projected onto a two-dimensional plane, enabling smooth and natural interpolation among a given set of landmark shapes, and transferring the generated variations to high-quality meshes.

GarmentCode: Programming Parametric Sewing Patterns

Maria Korosteleva (ETH Zurich), O. Sorkine-Hornung

CodeGenerationOptimizationAI Code AssistantPrompt EngineeringDiffusion modelAuto EncoderGenerative Adversarial NetworkImageTextMeshBenchmark

🎯 What it does: This paper proposes a domain-specific language called GarmentCode based on object-oriented programming, for generating programmable and interactive parameterized sewing patterns, and implements a garment configurator;

Interactive Story Visualization with Multiple Characters

Yuan Gong (Tsinghua University), Yujiu Yang (Tsinghua University)

CodeGenerationData SynthesisTransformerPrompt EngineeringVision Language ModelDiffusion modelContrastive LearningImageVideoText

🎯 What it does: A complete interactive story visualization system is proposed, which can generate multi-character images based on textual stories and produce animations.

iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis

Yash Kant (University of Toronto), Igor Gilitschenski (University of Toronto)

CodeGenerationData SynthesisDepth EstimationTransformerSupervised Fine-TuningDiffusion modelGaussian SplattingImagePoint CloudMesh

🎯 What it does: Propose the iNVS method, which uses a pre-trained 2D inpainting diffusion model to synthesize new views from a single input image.

Learning the Geodesic Embedding with Graph Neural Networks

Bo Pang (Peking University), Peng-Shuai Wang (Peking University)

CodeComputational EfficiencyRepresentation LearningGraph Neural NetworkAuto EncoderContrastive LearningMesh

🎯 What it does: Propose a GeGnn method based on graph neural networks to learn geodesic distance embeddings between two points on a surface, enabling constant-time distance queries after a single forward pass.

Low-Light Image Enhancement with Wavelet-Based Diffusion Models

Hailin Jiang, Shuaicheng Liu

CodeRestorationSuper ResolutionConvolutional Neural NetworkTransformerDiffusion modelImage

🎯 What it does: Proposed a condition diffusion model called DiffLL based on wavelet transform for low-light image enhancement.

Multiple-bounce Smith Microfacet BRDFs using the Invariance Principle

Yuang Cui (Anhui Science and Technology University), Beibei Wang (Nankai University)

CodeDiffusion modelImageBenchmarkPhysics Related

🎯 What it does: Propose a multi-bounce Smith microsurface BRDF model derived using the principle of invariance, and provide a concise paragraph function.

MuscleVAE: Model-Based Controllers of Muscle-Actuated Characters

Yusen Feng (Peking University), Libin Liu (Peking University)

CodeRobotic IntelligenceReinforcement LearningAuto EncoderWorld ModelVideoSequential

🎯 What it does: Proposes a muscle-driven character simulation and control framework based on the Hill muscle model and the 3CC-r fatigue model, and designs a muscle space PD control and a VAE-based generator controller called MuscleVAE.

Neural Gradient Learning and Optimization for Oriented Point Normal Estimation

Qing Li (Tsinghua University), Zhizhong Han (Wayne State University)

CodePose EstimationDepth EstimationOptimizationRepresentation LearningGraph Neural NetworkContrastive LearningPoint Cloud

🎯 What it does: Propose a two-stage framework based on deep learning—Neural Gradient Learning (NGL) and Gradient Vector Optimization (GVO)—for directly estimating consistently oriented normals from noisy, dense, and diverse point clouds.

Neural Metamaterial Networks for Nonlinear Material Design

Yue Li (ETH Zürich), Bernhard Thomaszewski (ETH Zürich)

CodeOptimizationComputational EfficiencyGraph Neural NetworkSpiking Neural NetworkTransformerDiffusion modelAuto EncoderContrastive LearningMeshGraphTabularTime SeriesPhysics RelatedStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: Proposed a neuro-morphological material network (NMN) for efficient inverse design of nonlinear morphological materials, directly optimizing structural parameters to match target stress-strain curves, directional stiffness, or Poisson's ratio curves.

Neural Stochastic Poisson Surface Reconstruction

Silvia Sellán, Alec Jacobson (University of Toronto)

CodeOptimizationComputational EfficiencyRepresentation LearningConvolutional Neural NetworkRecurrent Neural NetworkDiffusion modelScore-based ModelNeural Radiance FieldAuto EncoderContrastive LearningGaussian SplattingPoint CloudMesh

🎯 What it does: Propose a random masking Poisson reconstruction framework based on neural networks, representing both mean and covariance with multi-layer perceptrons, supporting efficient iterative updates, next best view planning, and seamless integration into the scanning process.

Object Motion Guided Human Motion Synthesis

Jiaman Li (Stanford University), C. K. Liu (Stanford University)

CodeGenerationData SynthesisPose EstimationTransformerDiffusion modelScore-based ModelVideoPoint CloudMesh

🎯 What it does: Generating complete human motions from object interactions.

Reach For the Spheres: Tangency-aware surface reconstruction of SDFs

Silvia Sell'an, Oded Stein (University of Southern California)

CodeOptimizationDiffusion modelScore-based ModelOptical FlowPoint CloudMeshStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: This paper proposes a global energy function that treats each SDF sample as a sphere and introduces tangent point constraints, achieving reconstruction from SDF to explicit triangle mesh via geometric flow gradient descent;

Reconstructing Close Human Interactions from Multiple Views

Qing Shuai (Zhejiang University), Xiaowei Zhou (Zhejiang University)

CodePose EstimationConvolutional Neural NetworkGraph Neural NetworkDiffusion modelAuto EncoderGenerative Adversarial NetworkContrastive LearningOptical FlowImagePoint CloudBenchmark

🎯 What it does: Propose a multi-view learning framework that utilizes a 3D conditional convolutional network to reconstruct the 3D poses of closely interacting crowds from 2D heatmaps captured by multiple cameras, effectively handling occlusions and identity confusion without relying on real image-3D paired data.

ReparamCAD: Zero-shot CAD Re-Parameterization for Interactive Manipulation

Milin Kodnongbua, Adriana Schulz

CodeOptimizationComputational EfficiencyData-Centric LearningTransformerLarge Language ModelVision Language ModelTextMesh

🎯 What it does: Developed ReparamCAD zero-shot pipeline, which infers the meaningful variation space of shapes using pre-trained large language models and image models, and reparameterizes CAD programs based on this, enabling easy exploration along meaningful design axes.

ReShader: View-Dependent Highlights for Single Image View-Synthesis

Avinash Paliwal (Texas A&M University), N. Kalantari (Texas A&M University)

CodeGenerationData SynthesisConvolutional Neural NetworkTransformerDiffusion modelNeural Radiance FieldAuto EncoderContrastive LearningImagePoint Cloud

🎯 What it does: Propose to decompose single-image novel view synthesis into two steps: pixel re-coloring and pixel re-localization. After training a specialized re-coloring network, combine it with existing re-localization methods to generate new views with perspective-dependent highlights that move naturally.

Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Covering

Fei Hou (Chinese Academy of Sciences), Ying He (Nanyang Technological University)

CodeOptimizationComputational EfficiencyRepresentation LearningMixture of ExpertsDiffusion modelAuto EncoderContrastive LearningOptical FlowPoint CloudMeshGraphStochastic Differential Equation

🎯 What it does: Propose a method called DoubleCoverUDF, which utilizes the double covering structure of r-offset and coverage mapping learning to robustly extract zero-level sets from the learned unsigned distance field (UDF), supporting both open and closed 3D surfaces.

Self-Calibrating, Fully Differentiable NLOS Inverse Rendering

Kiseok Choi (KAIST), Min H. Kim (KAIST)

CodeOptimizationDiffusion modelScore-based ModelNeural Radiance FieldOptical FlowImagePoint CloudPhysics Related

🎯 What it does: This paper proposes an end-to-end differentiable NLOS inverse rendering pipeline, capable of self-calibrating imaging parameters and reconstructing hidden scene surface points, normals, and albedo;

ShaDDR: Interactive Example-Based Geometry and Texture Generation via 3D Shape Detailization and Differentiable Rendering

Qimin Chen (Simon Fraser University), Hao Zhang (Simon Fraser University)

CodeGenerationData SynthesisConvolutional Neural NetworkSupervised Fine-TuningDiffusion modelNeural Radiance FieldAuto EncoderGenerative Adversarial NetworkImagePoint CloudMesh

🎯 What it does: A example-driven deep generative network called ShaDDR is constructed, which can refine rough voxel models into high-resolution, textured 3D shapes in less than 1 second.

SinMPI: Novel View Synthesis from a Single Image with Expanded Multiplane Images

Guo Pu (Peking University), Zhouhui Lian (Peking University)

CodeGenerationData SynthesisDepth EstimationTransformerDiffusion modelNeural Radiance FieldAuto EncoderContrastive LearningGaussian SplattingImage

🎯 What it does: Propose a single-image view synthesis method called SinMPI, which generates high-quality, freely rotatable 3D-consistent novel views by constructing an extended multi-plane image (MPI).

UVDoc: Neural Grid-based Document Unwarping

Floor Verhoeven (ETH Zurich), O. Sorkine-Hornung

CodeRestorationConvolutional Neural NetworkDiffusion modelScore-based ModelFlow-based ModelRectified FlowNeural Radiance FieldAuto EncoderContrastive LearningImageMeshBenchmark

🎯 What it does: Propose a single-image document de-warping method based on a dual-headed fully convolutional network, utilizing 3D meshes and 2D inverse mappings to jointly predict and achieve document de-warping.

VET: Visual Error Tomography for Point Cloud Completion and High-Quality Neural Rendering

Linus Franke (Friedrich-Alexander-Universität Erlangen-Nürnberg), Marc Stamminger (Friedrich-Alexander-Universität Erlangen-Nürnberg)

CodeRestorationGenerationSuper ResolutionComputational EfficiencyConvolutional Neural NetworkTransformerDiffusion modelNeural Radiance FieldAuto EncoderContrastive LearningGaussian SplattingImageVideoPoint Cloud

🎯 What it does: Proposes a point cloud completion and neural rendering framework based on Visual Error Tomography (VET), which can automatically clean and complete sparse or missing geometric structures.

What is the Best Automated Metric for Text to Motion Generation?

Jordan Voas (University of Texas at Austin), Raymond Mooney (University of Texas at Austin)

CodeGenerationData SynthesisPose EstimationTransformerSupervised Fine-TuningVision-Language-Action ModelContrastive LearningTextMultimodality

🎯 What it does: This paper systematically evaluates various automated evaluation metrics for the task of generating skeletal motions from natural language, and proposes a novel multimodal BERT-style evaluation model called MoBERT.