TriFlow synthesizes nearest-vertex vector fields via flow-matching to generate artist-like 3D mesh topology, then extracts meshes via clustering and topology-aware QEM simplification.
hub Canonical reference
Graph.42, 4, Article 139 (jul 2023), 14 pages
Canonical reference. 75% of citing Pith papers cite this work as background.
39
Pith papers citing it
4,766
external citations · Crossref
Background
75% of classified citations
hub tools
citation-role summary
background 5
method 3
citation-polarity summary
fields
cs.CV 21 cs.GR 6 eess.SP 3 cs.HC 2 physics.optics 2 cs.CR 1 cs.LG 1 cs.RO 1 eess.IV 1 physics.flu-dyn 1years
2026 39representative citing papers
Introduces Normalized Anisotropic Spherical Gabor function for efficient high-frequency view-dependent appearance modeling in radiance fields, claiming superior quality to low-order spherical harmonics with up to 5x better memory efficiency.
TIDES simulates realistic event camera streams in continuous time via dynamic Gaussian splatting with adaptive occlusion handling and sensor artifact modeling, claiming SOTA fidelity and better downstream transfer than prior methods.
Vector Scaffolding uses Interior Gradient Aggregation, Progressive Stratification, and Rapid Inflation Scheduling to achieve 2.5x faster optimization and up to 1.4 dB higher PSNR in differentiable vectorization.
AdpSplit adaptively splits Gaussians using pixel-error statistics to reduce 3DGS training time by 9-22% without quality loss.
S2C-3D reconstructs complete high-fidelity 3D scenes from as few as 6-8 images by finetuning a diffusion model on scene data, applying consistency-conditioned sampling, and planning trajectories for full coverage.
TouchPort collapses the multi-stage process of discovering, consenting to, and syncing mixed reality encounters into one embodied handshake-and-pull gesture.
SSD-GS decomposes 3D Gaussian Splatting reflectance into diffuse, specular, shadow, and subsurface scattering using a dipole scattering module, occlusion-aware shadows, and anisotropic Fresnel specular for photorealistic novel lighting.
Free-Range Gaussians uses flow matching over Gaussian parameters to predict non-grid-aligned 3D Gaussians from multi-view images, enabling synthesis of plausible content in unobserved regions with fewer primitives than grid-aligned methods.
Vis4GS is a multi-view visual analytics system for diagnosing 3DGS reconstruction artifacts by linking scene-level issues to primitive-level properties, view coverage, and optimization history.
3D Gaussian transient rendering enables NLOS imaging from arbitrary relay geometries in both confocal and non-confocal setups, achieving SOTA on real measurements.
VideoMDM learns coherent 3D motion manifolds from 2D supervision alone by using a pretrained lifter as noisy teacher, depth-weighted 2D reprojection loss, and adapted regularizers, nearly matching fully 3D-supervised performance on HumanML3D.
Scene-adaptive nonlinear tone curves (ASE and AP3) with percentile normalisation and offset outperform linear gain for pseudo-GT generation in low-light 3DGS, delivering PSNR gains up to 4.34 dB on LOM and 3.25 dB on RealX3D across 21 scenes.
EvoGS proposes the first continuous-layering 3D Gaussian Splatting representation via an Evolution Tree to reduce splat redundancy and transmission costs for scalable streaming.
AtlasGS uses shared subject-specific Gaussian geometry learned from isotropic scans to achieve through-plane super-resolution and multi-modal harmonization in brain MRI with reported state-of-the-art fidelity on UK Biobank, GBM, and ABCD datasets.
Topo-GS repurposes 3D Gaussian Splatting with local geometric constraints and topology-aware losses to produce continuous volumetric embeddings of high-dimensional data.
PG-3DGS couples 3D Gaussian Splatting with differentiable physics so that optimized shapes satisfy both visual fidelity and physical objectives such as pouring and aerodynamic lift, with real-world 3D-printed validation.
A conditional point-cloud flow matching model maps motor actuation to 3D geometry of tendon-driven continuum robots and outperforms prior self-modeling methods on simulated and real 2- and 3-module hardware.
PropSplat uses optimized 3D Gaussians initialized on transmitter-receiver paths to achieve lower RMSE than NeRF2, GSRF, and WRF-GS+ on outdoor drive-test and indoor BLE datasets while enabling map-free RF reconstruction.
A generative-AI pipeline dynamically generates and anchors virtual assets to match the shape of physical props, enabling adaptive passive haptics in MR that users rate higher in realism, immersion, and enjoyment than static baselines.
Any3DAvatar reconstructs full-head 3D Gaussian avatars from one image via one-step denoising on a Plücker-aware scaffold plus auxiliary view supervision, beating prior single-image methods on fidelity while running substantially faster.
The paper releases SignNet-1M, a 1M-scale augmented dataset for ASL, CSL and DGS with 3DGS and diffusion-based variations, plus benchmarks showing improved cross-shift generalization.
PC-TGS extrapolates APS to unmeasured grids by modeling scatterers as anisotropic 3D Gaussians from LiDAR data, using tangent-plane projection and depth-aware splatting with a closed-form integration.
An adaptive multi-criteria feature selection policy for 3D scene reconstruction that outperforms random, texture-only, and uniform-grid baselines on synthetic multi-view tests for completeness and RMSE.
citing papers explorer
-
TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields
TriFlow synthesizes nearest-vertex vector fields via flow-matching to generate artist-like 3D mesh topology, then extracts meshes via clustering and topology-aware QEM simplification.
-
Beyond Spherical Harmonics: Rethinking Appearance Models for Radiance Reconstruction
Introduces Normalized Anisotropic Spherical Gabor function for efficient high-frequency view-dependent appearance modeling in radiance fields, claiming superior quality to low-order spherical harmonics with up to 5x better memory efficiency.
-
TIDES: Time-Derivative Event Simulation via Deformable Reconstruction
TIDES simulates realistic event camera streams in continuous time via dynamic Gaussian splatting with adaptive occlusion handling and sensor artifact modeling, claiming SOTA fidelity and better downstream transfer than prior methods.
-
Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization
Vector Scaffolding uses Interior Gradient Aggregation, Progressive Stratification, and Rapid Inflation Scheduling to achieve 2.5x faster optimization and up to 1.4 dB higher PSNR in differentiable vectorization.
-
AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting
AdpSplit adaptively splits Gaussians using pixel-error statistics to reduce 3DGS training time by 9-22% without quality loss.
-
Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes
S2C-3D reconstructs complete high-fidelity 3D scenes from as few as 6-8 images by finetuning a diffusion model on scene data, applying consistency-conditioned sampling, and planning trajectories for full coverage.
-
Allow Me Into Your Dream: A Handshake-and-Pull Protocol for Sharing Mixed Realities in Spontaneous Encounters
TouchPort collapses the multi-stage process of discovering, consenting to, and syncing mixed reality encounters into one embodied handshake-and-pull gesture.
-
SSD-GS: Scattering and Shadow Decomposition for Relightable 3D Gaussian Splatting
SSD-GS decomposes 3D Gaussian Splatting reflectance into diffuse, specular, shadow, and subsurface scattering using a dipole scattering module, occlusion-aware shadows, and anisotropic Fresnel specular for photorealistic novel lighting.
-
Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction
Free-Range Gaussians uses flow matching over Gaussian parameters to predict non-grid-aligned 3D Gaussians from multi-view images, enabling synthesis of plausible content in unobserved regions with fewer primitives than grid-aligned methods.
-
Vis4GS: A Visual Analytic Tool for 3D Gaussian Splatting Reconstruction
Vis4GS is a multi-view visual analytics system for diagnosing 3DGS reconstruction artifacts by linking scene-level issues to primitive-level properties, view coverage, and optimization history.
-
Non-line-of-sight imaging with arbitrary relay surface geometries via 3D Gaussian Transient Rendering
3D Gaussian transient rendering enables NLOS imaging from arbitrary relay geometries in both confocal and non-confocal setups, achieving SOTA on real measurements.
-
VideoMDM: Towards 3D Human Motion Generation From 2D Supervision
VideoMDM learns coherent 3D motion manifolds from 2D supervision alone by using a pretrained lifter as noisy teacher, depth-weighted 2D reprojection loss, and adapted regularizers, nearly matching fully 3D-supervised performance on HumanML3D.
-
Scene-Adaptive Nonlinear Tone Curves for Pseudo Ground-Truth Generation in Low-Light 3D Gaussian Splatting
Scene-adaptive nonlinear tone curves (ASE and AP3) with percentile normalisation and offset outperform linear gain for pseudo-GT generation in low-light 3DGS, delivering PSNR gains up to 4.34 dB on LOM and 3.25 dB on RealX3D across 21 scenes.
-
EvoGS: Constructing Continuous-Layered Gaussian Splatting with Evolution Tree for Scalable 3D Streaming
EvoGS proposes the first continuous-layering 3D Gaussian Splatting representation via an Evolution Tree to reduce splat redundancy and transmission costs for scalable streaming.
-
AtlasGS: Brain MRI Spatial Resolution Harmonization With Shared Gaussian Geometry
AtlasGS uses shared subject-specific Gaussian geometry learned from isotropic scans to achieve through-plane super-resolution and multi-modal harmonization in brain MRI with reported state-of-the-art fidelity on UK Biobank, GBM, and ABCD datasets.
-
Topo-GS: Continuous Volumetric Embedding of High-Dimensional Data via Topological Gaussian Splatting
Topo-GS repurposes 3D Gaussian Splatting with local geometric constraints and topology-aware losses to produce continuous volumetric embeddings of high-dimensional data.
-
PG-3DGS: Optimizing 3D Gaussian Splatting to Satisfy Physics Objectives
PG-3DGS couples 3D Gaussian Splatting with differentiable physics so that optimized shapes satisfy both visual fidelity and physical objectives such as pouring and aerodynamic lift, with real-world 3D-printed validation.
-
Continuum Robot Modeling with Action Conditioned Flow Matching
A conditional point-cloud flow matching model maps motor actuation to 3D geometry of tendon-driven continuum robots and outperforms prior self-modeling methods on simulated and real 2- and 3-module hardware.
-
PropSplat: Map-Free RF Field Reconstruction via 3D Gaussian Propagation Splatting
PropSplat uses optimized 3D Gaussians initialized on transmitter-receiver paths to achieve lower RMSE than NeRF2, GSRF, and WRF-GS+ on outdoor drive-test and indoor BLE datasets while enabling map-free RF reconstruction.
-
Prop-Chromeleon: Adaptive Haptic Props in Mixed Reality through Generative Artificial Intelligence
A generative-AI pipeline dynamically generates and anchors virtual assets to match the shape of physical props, enabling adaptive passive haptics in MR that users rate higher in realism, immersion, and enjoyment than static baselines.
-
Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Image
Any3DAvatar reconstructs full-head 3D Gaussian avatars from one image via one-step denoising on a Plücker-aware scaffold plus auxiliary view supervision, beating prior single-image methods on fidelity while running substantially faster.
-
SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks
The paper releases SignNet-1M, a 1M-scale augmented dataset for ASL, CSL and DGS with 3DGS and diffusion-based variations, plus benchmarks showing improved cross-shift generalization.
-
Point-Cloud-Assistant Localized Statistical Channel Prediction by Tangent Gaussian Splatting
PC-TGS extrapolates APS to unmeasured grids by modeling scatterers as anisotropic 3D Gaussians from LiDAR data, using tangent-plane projection and depth-aware splatting with a closed-form integration.
-
Feature-Optimized Vision for Adaptive 3D Scene Reconstruction
An adaptive multi-criteria feature selection policy for 3D scene reconstruction that outperforms random, texture-only, and uniform-grid baselines on synthetic multi-view tests for completeness and RMSE.
-
Generator-Refiner-Examiner: A Tri-Module Data Augmentation Framework for 3D Human Avatar Learning from Monocular Videos
TrioMan is a tri-module data augmentation framework using a Generator for pose/camera perturbations, a Refiner with one-step diffusion, and an Examiner with dual-branch attention to improve 3D avatar learning from monocular videos, claiming better results than prior methods on two benchmarks.
-
Eff-WRFGS: Efficient Wireless Radiance Field Using 3D Gaussian Splatting
Eff-WRFGS prunes 3D Gaussian primitives via learnable masks to deliver up to 44x storage reduction and 7x faster rendering for wireless radiance fields on the NeRF² dataset with marginal quality loss.
-
Reality Check: How Avatar and Face Representation Affect the Perceptual Evaluation of Synthesized Gestures
Avatar appearance and facial presentation systematically bias perceptual judgments of synthesized co-speech gestures.
-
Age Verification in the Web -- Holy Grail to Control Access to Restricted Content
A privacy-preserving age verification approach for the web is proposed by adapting open cryptographic standards like Privacy Pass to let users prove age via trusted providers without special software or centralized data collection.
-
Hybrid Latents: Geometry-Appearance-Aware Surfel Splatting
A hybrid Gaussian-hash-grid representation with latent features and hard opacity falloffs reconstructs scenes more accurately than prior Gaussian splatting methods while using an order of magnitude fewer primitives.
-
MSGS: Multispectral 3D Gaussian Splatting
MSGS augments 3D Gaussian Splatting with spectral radiance via per-band spherical harmonics and dual-loss supervision to improve multispectral view synthesis quality and consistency over RGB-only baselines.
-
Low-Cost Continuous-Wave Diffusive Microtomography with Fiber-Scanned White-Light Illumination
Low-cost CWDT system with fiber-scanned illumination and ML-tuned forward model yields qualitative volumetric reconstructions from cleared poplar, scattering phantoms, and fungal samples.
-
AnisoLift: Anisotropic Latent Representations for Coarse Particle Liquid Enhancement
AnisoLift augments coarse particles with anisotropic ellipsoids and predicts residual state corrections to improve fidelity to high-resolution liquid flows.
-
Gaussian Field Representations for Turbulent Flow: Compression, Scale Separation, and Physical Fidelity
Gaussian primitives compress 3D Taylor-Green vortex flows at ratios over 1000x while preserving velocity but degrading enstrophy, with anisotropic extensions recovering small-scale vortical structures better than baseline or other variants.
-
Comparative evaluation of photogrammetric reconstruction methods and 3D Gaussian Splatting for road surface roughness analysis
COLMAP shows highest micro-texture sensitivity while open-source tools prove viable for relative road roughness estimation from images.
-
Large-Scale Photogrammetric Documentation of St. John's Co-Cathedral: A Workflow for Cultural Heritage Preservation
A complete multi-modal photogrammetry pipeline that produced a 25-30 billion triangle 3D model of St. John's Co-Cathedral while addressing reflective surfaces and low-light conditions through strategic capture, AI denoising, and hybrid reconstruction.
-
Deep Learning Approaches for 3D Medical Scene Completion: From Geometric Modeling to Generative Paradigms
A literature survey that compiles ten years of 3D scene completion research, builds a taxonomy of representation paradigms, and outlines a future research agenda.
- HyperBones: Realtime Bone-driven Neural Garment Simulation with Hypernetwork Conditioning
- A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation
- FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles