archive
Every paper Pith has read. Search by title, abstract, or pith.
456 papers in cs.GR · page 3
-
Parts and optical flow improve dynamic Gaussian splatting
PaMoSplat: Part-Aware Motion-Guided Gaussian Splatting for Dynamic Scene Reconstruction
-
Generative tools map creative goals to particle VFX parameters
Elemental Alchemist: A Generative Interface for Semantic Control of Particle Systems Across Dynamic Levels of Abstraction
-
Curated synthetic images boost real pose baselines at low cost
A Real-Calibrated Synthetic-First Data Engine
-
Anchored Gaussians track wireframe deformations from sparse views
FrameTwin: Curve-Anchored Gaussian Alignment from Sparse Views for Adaptive Wireframe 3D Printing
-
Divergence-free kernels advect Gaussian splats to reconstruct fluid velocities
LagrangianSplats: Divergence-Free Transport of Gaussian Primitives for Fluid Reconstruction
-
Color-adaptive scheme raises 3D Gaussian streaming quality 5-20 dB
CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting
-
Transformer simulates rigid dynamics from point clouds without meshes
RigidFormer: Learning Rigid Dynamics using Transformers
-
Gaussian splatting relights VP scenes by sampling LED backgrounds directly
Relightable Gaussian Splatting for Virtual Production Using Image-Based Illumination
-
Random slicing with NW smoothing speeds up topological optimization
Towards Scalable Persistence-Based Topological Optimization
-
Neural network adapts frame rate and resolution for better streamed graphics
Streaming of rendered content with adaptive frame rate and resolution
-
Strand sequences turn 3D hair generation into semantic authoring
HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis
-
Targeted region regeneration fixes low-poly meshes locally
MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation
-
Unison aligns motion, speech and sound in video generation
Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation
-
Density sampling over octrees adapts Gaussians for image-to-3D
Generative 3D Gaussians with Learned Density Control
-
Local bone mappings stabilize garment refitting on varied bodies
LoBoFit: Flexible Garment Refitting via Local Bone Mapping Blending
-
Local 3D edits done inside the velocity sampler
Velocity-Space 3D Asset Editing
-
Polynomial kernel sharpens 3D surfaces from multi-view photos
High-Fidelity Surface Splatting-Based 3D Reconstruction from Multi-View Images
-
Semantic codebook creates style-matched co-speech gestures
PersonaGest: Personalized Co-Speech Gesture Generation with Semantic-Guided Hierarchical Motion Representation
-
Physics simulation and RL automate motion retargeting for robots
ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting
-
Avatar and face choice changes gesture quality ratings
Reality Check: How Avatar and Face Representation Affect the Perceptual Evaluation of Synthesized Gestures
-
Avatar visuals shift ratings of synthesized gestures
Reality Check: How Avatar and Face Representation Affect the Perceptual Evaluation of Synthesized Gestures
-
Kernel-based opacity turns surface splats into a differentiable renderer
3DSS: 3D Surface Splatting for Inverse Rendering
-
Surface splatting made differentiable for shape and material recovery
3DSS: 3D Surface Splatting for Inverse Rendering
-
Kernel-derived opacity turns surface splatting differentiable for inverse rendering
3DSS: 3D Surface Splatting for Inverse Rendering
-
LLM and RL coupling with VR feedback creates adaptive 3D scenes
Closing the Loop: Unified 3D Scene Generation and Immersive Interaction via LLM-RL Coupling
-
Delighting prior extracts reflectance from casual face videos
Learning a Delighting Prior for Facial Appearance Capture in the Wild
-
Sano model best matches shell results on ribbon buckling shifts
Discrete Elastic Ribbons: A Unified Discrete Differential Geometry Framework for One-Dimensional Energy Models
-
Bayesian view selection cuts scans needed for task-specific 3D models
A Bayesian Approach for Task-Specific Next-Best-View Selection with Uncertain Geometry
-
QuadBox speeds up 3D Gaussian Splatting by 1.85 times
QuadBox: Accelerating 3D Gaussian Splatting with Geometry-Aware Boxes
-
Algebraic coarsening delivers 3x speedup in GPU contact solves
AGIPC: Adaptive In-Solve Algebraic Coarsening for GPU IPC
-
Single photo yields head mesh with pro-ready topology
High-Fidelity Single-Image Head Modeling with Industry-Grade Topology
-
CoherentRaster enables real-time light field rendering
CoherentRaster: Efficient 3D Gaussian Splatting for Light Field Displays
-
Precomputed maps simulate real lens optics an order of magnitude faster
Precomputed Lens Transport Maps
1 Piths -
Single photo produces 3D face via 3DMM regression
3D Human Face Reconstruction with 3DMM face model from RGB image
-
Bidirectional loop boosts spatial intelligence in unified visual model
JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
-
Unified model links understanding and editing to build spatial intelligence
JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
-
Algorithm distributes points on curved surfaces with prescribed local spacing
Globally adaptive and locally regular point discretization of curved surfaces
-
Cumulative maps let diffusion models generate in one step
A Few-Step Generative Model on Cumulative Flow Maps
-
Delaunay scaffold samples implicit surfaces with 10x fewer evaluations
ADS: Random Sampling of Occupancy Functions using Adaptive Delaunay Scaffolding
-
Zero sets of complex sections produce bijective surface maps
Implicit Minimal Surfaces for Bijective Correspondences
-
Adaptive layer speeds animation in-betweening by 3.5 times
Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animation
-
Surface correspondence tracking yields clean structural MATs
Structural MAT: Clean and Scalable Medial Axis Simplification via Explicit Surface Correspondence
-
Recursive successor lists speed k-NN on manifolds by 1-10x
Manifold k-NN: Accelerated k-NN Queries for Manifold Point Clouds
-
Orbit-space flows match 3D shape SOTA with 5x fewer steps
Generative Modeling with Orbit-Space Particle Flow Matching
-
GETA-3DGS cuts 3D Gaussian Splatting storage fivefold automatically
GETA-3DGS: Automatic Joint Structured Pruning and Quantization for 3D Gaussian Splatting
-
CADFS dataset powers AI to generate complex CAD programs
CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models
-
Greedy algorithm keeps signed distance interpolations consistent
Greed for the Spheres: A Signed Distance Interpolation Method
-
Pruned local blendshapes run 2K avatars at 120 FPS on phones
High-Fidelity Mobile Avatars with Pruned Local Blendshapes
-
The paper introduces the Antipodal Method
The Antipodal Method: Fast, Accurate, and Robust 3D Generalized Winding Numbers
-
Historians employ visualizations in five distinct roles
How Historians Use Visualization: A Corpus-Backed Taxonomy and Analysis for Cross-Disciplinary Practice