arXivSub Start free trial

SIGGRAPH Asia 2025 Papers with Code

ACM SIGGRAPH Asia (Transactions on Graphics) · 41 papers with a public code repository

3D SMoE Splatting for Edge-aware Realtime Radiance Field Rendering

Yi-Hsin Li, Mårten Sjöström

CodeOptimizationComputational EfficiencyMixture of ExpertsNeural Radiance FieldGaussian SplattingPoint Cloud

🎯 What it does: Proposed a new 3D SMoE Splatting (3DSMoES) framework, integrating the Steered Mixtures-of-Experts regression method into the CUDA-optimized process of 3D Gaussian Splatting (3DGS) to achieve 3D rendering.

A Stack-Free Parallel h-Adaptation Algorithm for Dynamically Balanced Trees on GPUs

Lixin Ren, Enhua Wu

CodeOptimizationComputational Efficiency

🎯 What it does: Developed a stackless parallel h-adaptive algorithm for GPUs for the construction and update of dynamic balanced trees to improve fluid simulation performance

AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models

Zehuan Huang (Beihang University), Lu Sheng (Beihang University)

CodeGenerationData SynthesisPose EstimationTransformerPrompt EngineeringVision-Language-Action ModelDiffusion modelAuto EncoderGenerative Adversarial NetworkContrastive LearningVideoTextMeshSequential

🎯 What it does: Achieved text-driven animation generation for 3D meshes with arbitrary skeletal structures through a joint video-pose diffusion model.

AutoBrep : Autoregressive B-Rep Generation with Unified Topology and Geometry

Xiang Xu (Autodesk Research), Peter Meltzer

CodeGenerationData SynthesisTransformerLarge Language ModelSupervised Fine-TuningDiffusion modelAuto EncoderPoint CloudMesh

🎯 What it does: Proposed and trained a single autoregressive Transformer called AutoBrep, which generates complete B-Reps using a unified discrete token sequence based on face-edge topology, supporting auto-completion.

CameraVDP: Perceptual Display Assessment with Uncertainty Estimation via Camera and Visual Difference Prediction

Yancheng Cai (University of Cambridge), Rafal Mantiuk

CodeAnomaly DetectionOptimizationExplainability and InterpretabilityComputational EfficiencyDiffusion modelScore-based ModelContrastive LearningGaussian SplattingOptical FlowImageVideoPoint Cloud

🎯 What it does: Propose a complete display evaluation system called CameraVDP, which combines a calibrated consumer-grade camera with a visual difference predictor. It can achieve precise photometric, color, and geometric correction on the original images captured by the camera, and assess human-perceptible display defects through the visual difference predictor, while providing uncertainty estimation.

Can Any Model Be Fabricated? Inverse Operation Based Planning for Hybrid Additive-Subtractive Manufacturing

Yongxue Chen (University of Manchester), Charlie C. L. Wang

CodeOptimizationComputational EfficiencyRobotic IntelligenceDiffusion modelAuto EncoderContrastive LearningPoint CloudMeshBenchmark

🎯 What it does: Propose an inverse operation (accretion and erosion) planning algorithm that can generate executable hybrid additive-subtractive manufacturing sequences for any complex geometry, ensuring that the final part is completely consistent with the target geometry.

Clustered Error Correction with Grouped 4D Gaussian Splatting

Taeho Kang (Seoul National University), Youngki Lee (Seoul National University)

CodeRestorationGenerationOptimizationDiffusion modelGaussian SplattingOptical FlowVideoPoint CloudBenchmark

🎯 What it does: An improved method based on clustering error correction and group dynamic transformation is proposed for 4D Gaussian point cloud rendering. It uses elliptical error clustering to locate missing or occluded errors and dynamically adds new Gaussian points through back-projection or foreground segmentation. At the same time, group-shared temporal transformations are introduced to maintain consistent correspondence between dynamic objects and point clouds.

DvD: Unleashing a Generative Paradigm for Document Dewarping via Coordinates-based Diffusion Model

Weiguang Zhang (Xi'an Jiaotong-Liverpool University), Qiufeng Wang (Xi'an Jiaotong-Liverpool University)

CodeRestorationTransformerDiffusion modelContrastive LearningImageMultimodalityBenchmark

🎯 What it does: Propose DvD, a document dewarping method based on coordinate-level diffusion models, which generates dewarping mappings instead of directly generating images, and construct a large-scale multi-domain evaluation benchmark called AnyPhotoDoc6300.

FreeMusco: Motion-Free Learning of Latent Control for Morphology-Adaptive Locomotion in Musculoskeletal Characters

Minkwan Kim (Hanyang University), Yoonsang Lee (Hanyang University)

CodeRobotic IntelligenceTransformerReinforcement LearningDiffusion modelAuto EncoderContrastive LearningWorld ModelTime SeriesSequential

🎯 What it does: This paper proposes a 'FreeMusco' framework that does not rely at all on motion capture data. It can jointly learn the latent gait representation and low-level control strategies of musculoskeletal characters, achieving energy-aware, morphology-adaptive diverse gaits, and can further be used for high-level tasks such as target navigation and path following.

GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats

Kai Deng (Nankai University), Jin Xie (Nankai University)

CodeDepth EstimationAutonomous DrivingOptimizationComputational EfficiencyConvolutional Neural NetworkRecurrent Neural NetworkNeural Radiance FieldGaussian SplattingSimultaneous Localization and MappingOptical FlowImageVideoPoint Cloud

🎯 What it does: Proposes GigaSLAM, a monocular RGB odometry and mapping framework that utilizes a hierarchical sparse voxel structure and Gaussian projection rendering, enabling real-time localization and high-quality scene rendering in kilometer-scale, unbounded outdoor environments.

High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation

Jiahao Cui, Siyu Zhu

CodeGenerationData SynthesisReinforcement Learning from Human FeedbackConvolutional Neural NetworkTransformerDiffusion modelImageVideoAudio

🎯 What it does: Proposes a diffusion framework based on human preference alignment for high-dynamic, realistic portrait animation driven by audio and skeletal motion.

HRM^2Avatar: High-Fidelity Real-Time Mobile Avatars from Monocular Phone Scans

Chao Shi (Alibaba Group), Chengfei Lv (Alibaba Group)

CodeGenerationOptimizationComputational EfficiencyConvolutional Neural NetworkTransformerDiffusion modelNeural Radiance FieldAuto EncoderContrastive LearningGaussian SplattingOptical FlowImageVideoMesh

🎯 What it does: Proposed an end-to-end single-phone scanning workflow that utilizes two-phase static and dynamic video sequences to construct high-fidelity full-body clothing avatars that can be rendered in real-time on mobile devices;

Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation

Xiaoming Zhu (Tsinghua University), Long Zeng (Tsinghua University)

CodeGenerationPose EstimationDepth EstimationRetrievalTransformerPrompt EngineeringVision Language ModelDiffusion modelScore-based ModelImageTextPoint CloudMeshRetrieval-Augmented Generation

🎯 What it does: A visually driven system is proposed, which can generate high-quality, logically coherent 3D scene layouts from a predefined 3D asset library by combining text prompts, refined image generation models, image parsing, and asset retrieval.

Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization

Yang You (Stanford University), Leonidas J. Guibas (Stanford University)

CodeImage TranslationGenerationData SynthesisConvolutional Neural NetworkTransformerSupervised Fine-TuningPrompt EngineeringVision Language ModelFlow-based ModelImagePoint CloudMesh

🎯 What it does: A two-stage framework called Img2CAD is constructed, which first uses a VLM to predict the discrete CAD structure from a single-view image, and then employs a Transformer to predict continuous attributes, thereby achieving reverse engineering from images to 3D CAD.

Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation

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

CodeGenerationData SynthesisComputational EfficiencyKnowledge DistillationTransformerDiffusion modelScore-based ModelContrastive LearningImageVideoAudio

🎯 What it does: Propose a conditional video distillation method that realizes real-time lip-sync video generation using input human pose information, combining input-aware sparse attention and distillation loss.

Large-Area Fabrication-aware Computational Diffractive Optics

Kaixuan Wei (King Abdullah University of Science and Technology), Wolfgang Heidrich (King Abdullah University of Science and Technology)

CodeOptimizationConvolutional Neural NetworkDiffusion modelAuto EncoderImagePoint CloudTabularPhysics Related

🎯 What it does: We have designed and implemented a differentiable optical design framework aimed at large-area, mass-producible applications, taking into account process distortions and numerical high-resolution capabilities. It combines grayscale direct-write photolithography plus nanoimprint replication, utilizing a neural network digital twin to achieve process modeling, and employs GSPMD distributed FFT and convolution for large-scale DOE optimization.

LookUp3D: Data-Driven 3D Scanning

Giancarlo Pereira (New York University), D. Panozzo

CodeDepth EstimationGaussian SplattingSimultaneous Localization and MappingOptical FlowPoint CloudMesh

🎯 What it does: Propose LookUp3D, a structured light 3D scanning method based on a per-pixel color-to-depth lookup table, capable of acquiring high-resolution 3D geometry at high frame rates.

Low-Rank Adaptation of Neural Fields

Anh Truong (Massachusetts Institute of Technology), Justin Solomon (Massachusetts Institute of Technology)

CodeRestorationCompressionOptimizationComputational EfficiencySupervised Fine-TuningNeural Radiance FieldImageVideoPoint CloudMesh

🎯 What it does: Proposes a parameter-efficient update method for instance-specific neural fields using low-rank adaptation (LoRA), which can encode minor edits (such as image filtering, geometric deformation, video compression, energy minimization) as low-rank weight increments;

LSF-Animation: Label-Free Speech-Driven Facial Animation via Implicit Feature Representation

Xin Lu (University of Chinese Academy of Sciences), Jun Xiao (University of Chinese Academy of Sciences)

CodeGenerationRepresentation LearningTransformerDiffusion modelAuto EncoderGenerative Adversarial NetworkContrastive LearningMultimodalityMeshAudio

🎯 What it does: A fully unlabeled voice-driven 3D facial animation framework, LSF-Animation, was developed, which can directly extract emotional and identity features from raw audio and neutral facial meshes, achieving unlabeled generation.

MODepth: Benchmarking Mobile Multi-frame Monocular Depth Estimation with Optical Image Stabilization

Yu Lu, Guangtao Xue

CodeDepth EstimationOptimizationComputational EfficiencyConvolutional Neural NetworkTransformerAuto EncoderContrastive LearningOptical FlowImageVideoBenchmark

🎯 What it does: Proposed a multi-frame monocular depth estimation system called MODepth, which is based on controlling motion through an optical image stabilization (OIS) module, and designed the MODNet network as well as the principal point offset estimation module and the pose estimation module.

MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis

Yihao Zhi (CUHKSZ), Xiaoguang Han (CUHKSZ)

CodeGenerationData SynthesisPose EstimationDepth EstimationTransformerDiffusion modelAuto EncoderGenerative Adversarial NetworkContrastive LearningOptical FlowImageVideo

🎯 What it does: Proposed MV-Performer, a framework that converts monocular videos into synchronized multi-view 360-degree human novel view synthesis.

Neural Octahedral Field: Octahedral Prior for Simultaneous Smoothing and Sharp Edge Regularization

Ruichen Zheng (Tsinghua University), Ruizhen Hu (Shenzhen University)

CodeRestorationDiffusion modelScore-based ModelNeural Radiance FieldAuto EncoderContrastive LearningPoint CloudMesh

🎯 What it does: By introducing the Neural Octahedral Field (NOF) as a prior, simultaneous point cloud denoising and adaptive regularization of smooth and sharp edges are achieved for neural implicit surfaces, thereby recovering clearer and more sharply featured 3D surfaces from noisy point clouds.

Neural Visibility of Point Sets

Jun-Hao Wang (Peking University), Peng-Shuai Wang (Peking University)

CodeClassificationComputational EfficiencyRepresentation LearningConvolutional Neural NetworkGraph Neural NetworkVision Language ModelAuto EncoderContrastive LearningPoint CloudMesh

🎯 What it does: This paper proposes a deep learning-based method for point cloud visibility determination, directly predicting the visibility of each point under a given viewpoint;

NeuralPVS: Learned Estimation of Potentially Visible Sets

Xiangyu Wang, Dieter Schmalstieg

CodeDepth EstimationOptimizationComputational EfficiencyConvolutional Neural NetworkDiffusion modelScore-based ModelAuto EncoderContrastive LearningGaussian SplattingOptical FlowImageVideoPoint CloudMesh

🎯 What it does: Propose NeuralPVS, a real-time depth learning-based method for computing potential visibility sets (PVS) from regions, capable of outputting nearly error-free visible geometry sets at a frame rate of 100 Hz.

OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Models

D. Samuel, Rami Ben-Ari

CodeImage TranslationRestorationSegmentationGenerationTransformerDiffusion modelAuto EncoderOptical FlowImageVideoBenchmark

🎯 What it does: Propose OmnimatteZero, a fully training-free real-time video matting method that achieves object removal, foreground extraction, and layer composition while preserving object effects such as shadows and reflections.

PartComposer: Learning and Composing Part-Level Concepts from Single-Image Examples

Junyu Liu (Brown University), Daniel Ritchie (Brown University)

CodeGenerationData SynthesisTransformerSupervised Fine-TuningDiffusion modelContrastive LearningImageMultimodality

🎯 What it does: Learn and combine fine-grained part concepts from a single image to achieve cross-category controllable generation

PoissonNet: A Local-Global Approach for Learning on Surfaces

Arman Maesumi (Brown University), Noam Aigerman (Université de Montréal)

CodeClassificationSegmentationPose EstimationRepresentation LearningGraph Neural NetworkAuto EncoderContrastive LearningPoint CloudMesh

🎯 What it does: This paper proposes a novel graph learning framework called PoissonNet, which combines local gradient transformation and global Poisson equation solving to achieve efficient learning of surface features on triangular meshes.

PowerGS: Display-Rendering Power Co-Optimization for Neural Rendering in Power-Constrained XR Systems

Weikai Lin (University of Rochester), Yuhao Zhu (University of Rochester)

CodeOptimizationComputational EfficiencyNeural Radiance FieldGaussian SplattingImageVideoPoint Cloud

🎯 What it does: Proposes the PowerGS framework, which jointly optimizes the rendering power consumption and display power consumption of the 3D Gaussian Splatting (3DGS) model under the constraint of visual quality, and supports disparity rendering.

PractiLight: Practical Light Control Using Foundational Diffusion Models

Yotam Erel, C. Theobalt

CodeImage TranslationRestorationGenerationTransformerSupervised Fine-TuningPrompt EngineeringDiffusion modelImage

🎯 What it does: This paper proposes PractiLight, a method for controllable relighting that utilizes the base diffusion model (Stable Diffusion 1.5) to manipulate lighting and shadows. It trains a lightweight LoRA regressor on the self-attention layer to predict the direct-irradiance map of an image, and during image generation, it employs Classifier Guidance, ControlNet, and self-attention query injection techniques to freely modify the light source position, intensity, and material on the generated image.

Robust Single-shot Structured Light 3D Imaging via Neural Feature Decoding

Jiaheng Li, Wenzheng Chen

CodeData SynthesisDepth EstimationConvolutional Neural NetworkRecurrent Neural NetworkTransformerPrompt EngineeringNeural Radiance FieldAuto EncoderContrastive LearningOptical FlowImagePoint CloudMeshBenchmark

🎯 What it does: Propose a single-frame structured light 3D reconstruction framework called NSL based on neural feature decoding, which can achieve high-precision depth recovery under a single camera + projection mode;

Self-supervised Underwater Color Restoration via Wavelet-Diffusion Model with Filtered Multi-Scale Feature Distillation

Xin Zhang, Binghua Su

CodeRestorationTransformerDiffusion modelScore-based ModelContrastive LearningImage

🎯 What it does: Proposes a self-supervised underwater color restoration framework based on waveform diffusion models, utilizing filtered multi-scale feature distillation;

Shape-aware Inertial Poser: Motion Tracking for Humans with Diverse Shapes Using Sparse Inertial Sensors

Lu Yin (Xiamen University), Shihui Guo (Xiamen University)

CodePose EstimationOptimizationRecurrent Neural NetworkTransformerContrastive LearningOptical FlowMeshTime SeriesSequential

🎯 What it does: Proposes a shape-aware sparse inertial capture system, SAIP, which can achieve real-time motion capture for different body types (including children) using only six IMUs, and first realizes human shape estimation in IMU-based capture.

SOF: Sorted Opacity Fields for Fast Unbounded Surface Reconstruction

L. Radl, Markus Steinberger

CodeComputational EfficiencyRepresentation LearningDiffusion modelNeural Radiance FieldGaussian SplattingImagePoint CloudMesh

🎯 What it does: Propose the Sorted Opacity Fields (SOF) method, enabling the fast extraction of high-quality unbounded surface meshes from 3D Gaussian representations.

STGlight: Online Indoor Lighting Estimation via Spatio-Temporal Gaussian Fusion

Shiyuan Shen, Chunxia Xiao

CodeDepth EstimationComputational EfficiencyTransformerNeural Radiance FieldGaussian SplattingVideoPoint Cloud

🎯 What it does: Propose STGlight, a lightweight online indoor lighting estimation method that can process LDR RGB-D video streams, maintain incrementally updated global geometric and lighting representations, and predict HDR environment maps for any position in each frame.

Teamwork: Collaborative Diffusion with Low-rank Coordination and Adaptation

Sam Sartor (College of William & Mary), Pieter Peers (College of William & Mary)

CodeGenerationData SynthesisTransformerDiffusion modelImage

🎯 What it does: Proposes the Teamwork framework, which utilizes multi-instance low-rank adaptation and coordination mechanisms to achieve input/output channel expansion and task transfer without modifying the structure of pre-trained diffusion models.

Temporally Smooth Mesh Extraction for Procedural Scenes with Long-Range Camera Trajectories using Spacetime Octrees

Zeyu Ma (Princeton University), Jia Deng (Princeton University)

CodeGenerationData SynthesisNeural Radiance FieldGaussian SplattingOptical FlowPoint CloudMeshTime Series

🎯 What it does: Propose the BinocMesher method, which extracts temporally smooth 3D meshes from an occupancy function under long-distance camera trajectories using a 4D Binary-Octree.

TrackerSplat: Exploiting Point Tracking for Fast and Robust Dynamic 3D Gaussians Reconstruction

Daheng Yin (Simon Fraser University), Jiangchuan Liu (Simon Fraser University)

CodeObject TrackingOptimizationComputational EfficiencyNeural Radiance FieldContrastive LearningGaussian SplattingOptical FlowVideoPoint Cloud

🎯 What it does: By combining pixel trajectories from multi-view point tracking with a 3D Gaussian model, TrackerSplat rapidly and robustly reconstructs dynamic 3D scenes in multi-view videos.

Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation

Chenjie Cao (Alibaba), Yanwei Fu (Fudan University)

CodeGenerationData SynthesisDepth EstimationTransformerVision-Language-Action ModelDiffusion modelGaussian SplattingOptical FlowImageVideoPoint CloudMeshBenchmark

🎯 What it does: Propose the Uni3C framework, unifying 3D-enhanced camera trajectory control with human motion control, for generating high-quality controllable videos from single views.

UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images

Yiming Zhao (Peking University), Zhouhui Lian (Peking University)

CodeImage TranslationGenerationData SynthesisReinforcement Learning from Human FeedbackTransformerLarge Language ModelVision Language ModelDiffusion modelRectified FlowAuto EncoderImageTextMultimodalityBenchmark

🎯 What it does: Propose the UTDesign unified framework to achieve high-precision stylized text editing and generation of English labels in design images, and integrate a complete text-to-design (T2D) pipeline.

Vertex Features for Neural Global Illumination

Rui Su (Peking University), Sheng Li (Peking University)

CodeComputational EfficiencyRepresentation LearningGraph Neural NetworkDiffusion modelNeural Radiance FieldAuto EncoderContrastive LearningGaussian SplattingPoint CloudMesh

🎯 What it does: This paper proposes an encoding method that directly stores learnable features on the vertices of a 3D mesh (Neural Vertex Features), and combines adaptive multi-resolution refinement (LOD) to achieve efficient neural global illumination rendering.

Waste-to-Value: Reutilized Material Maximization for Additive and Subtractive Hybrid Remanufacturing

Fanchao Zhong, Haisen Zhao

CodeOptimizationGraph Neural NetworkPrompt Engineering

🎯 What it does: Propose a computational framework that strictly considers global and local collision constraints to plan the addition and subtraction of material hybrid remanufacturing processes in order to maximize the reusable volume.