An explicit model using learned 3D Gaussians for volume compression encodes geometry explicitly and outperforms implicit neural representations on unstructured volumes with faster training.
hub Canonical reference
Graph.42, 4, Article 139 (jul 2023), 14 pages
Canonical reference. 75% of citing Pith papers cite this work as background.
46
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 25 cs.GR 7 eess.SP 3 cs.HC 2 cs.LG 2 cs.RO 2 physics.optics 2 cs.CR 1 eess.IV 1 physics.flu-dyn 1years
2026 46representative citing papers
A regularization technique that treats diffusion model outputs as a similarity kernel during material optimization in inverse rendering, enabling joint reconstruction of geometry, materials, and illumination that satisfies the rendering equation and generalizes to new lighting.
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.
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.
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.
NURBS Splatting represents rational splines as continuous Gaussian fields sampled along the curve to enable stable differentiable rendering of vector graphics.
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.
DelowlightSplat adds a lightweight Lowlight Adapter and cost-volume multi-view inference to feed-forward Gaussian splatting, enabling direct prediction of clean 3D Gaussians from degraded lowlight context views.
HyperBones trains a reduced-space neural dynamics model with bone-driven coarse simulation and CNN-based wrinkle recovery to produce plausible garment motion at 300+ FPS using physics supervision without an external simulator.
Topo-GS repurposes 3D Gaussian Splatting with local geometric constraints and topology-aware losses to produce continuous volumetric embeddings of high-dimensional data.
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 image vectorization.
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.
citing papers explorer
-
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.
-
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.
-
A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation
A survey that categorizes deep learning models for point cloud tasks by backbone architecture, evaluates benchmark performance, and outlines challenges and future research directions.