archive
Every paper Pith has read. Search by title, abstract, or pith.
456 papers in cs.GR · page 5
-
Self-supervised models curate largest slow-motion video dataset
Seeing Fast and Slow: Learning the Flow of Time in Videos
-
Coprime pixel sizes yield stable super-resolution without priors
Multiscale Super Resolution without Image Priors
-
CUDA rasterizer outperforms Vulkan on 100M+ triangle meshes
CuRast: Cuda-Based Software Rasterization for Billions of Triangles
-
Calibrated encoders track face identity across artistic styles
StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
-
Method fits 3D bodies at millimeter accuracy from scans or images alone
OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction
-
Seed3D 2.0 wins 69-90 percent of votes against commercial 3D tools
Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
-
Serverless toolkit builds urban VA prototypes in hours
Autark: A Serverless Toolkit for Prototyping Urban Visual Analytics Systems
-
Framework adds animator control to skeleton generation on complex models
Animator-Centric Skeleton Generation on Objects with Fine-Grained Details
-
Stability simulation refines two-person object co-manipulation motions
Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation
-
Iteration lets Monte Carlo solvers handle nonlinear radiation boundaries
Monte Carlo PDE Solvers for Nonlinear Radiative Boundary Conditions
-
Incremental Woodbury updates speed contact sims up to 5.66x
An Efficient Multilevel Preconditioned Nonlinear Conjugate Gradient Method for Incremental Potential Contact
-
Superpower contours reconstruct surfaces from unsigned distances
SpUDD: Superpower Contouring of Unsigned Distance Data
-
Superpower contour from unsigned distances yields surface meshes
SpUDD: Superpower Contouring of Unsigned Distance Data
-
Reproduction rules extend the arrowhead curve to higher dimensions
Stitching Arrowhead Curves: Extending the Sierpinski Arrowhead Curve to Higher Dimensions
-
System turns sketches into real-time 3D head models
SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splatting
-
New Python tool turns SUMO data into 3D traffic videos
sumo3Dviz: A three dimensional traffic visualisation
-
JSON from panoramic views lets LLMs give NPCs spatial awareness
Empowering NPC Dialogue with Environmental Context Using LLMs and Panoramic Images
-
Transport mapping fills more UV slots in Gaussian Splatting
OT-UVGS: Revisiting UV Mapping for Gaussian Splatting as a Capacity Allocation Problem
-
Flux correction at T-junctions keeps multigrid consistent on octrees
Matrix-Free Multigrid with Algebraically Consistent Coarsening on Adaptive Octrees
-
Solo motions retargeted to enable cooperative humanoid tasks
SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy
-
Pipeline turns sparse driving views into complete 3D assets
Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation
-
Qwen 3 Coder tops Manim animations with GRPO and RITL-DOC
Training and Agentic Inference Strategies for LLM-based Manim Animation Generation
-
Cross-part transformer improves upper-body pose estimates
Chatting about Upper-Body Expressive Human Pose and Shape Estimation
-
Uncertainty in poses improves NeRF surface reconstructions
PCM-NeRF: Probabilistic Camera Modeling for Neural Radiance Fields under Pose Uncertainty
-
Video diffusion priors alone create valid pose spaces for rigged meshes
ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes
-
Video priors yield pose spaces for rigged meshes matching 4D models
ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes
-
MESA restores ancient inscriptions using multiple exemplars without training
MESA: A Training-Free Multi-Exemplar Deep Framework for Restoring Ancient Inscription Textures
-
New bases evaluate Gauss-Legendre curves in O(n^{2} + dn) time
Evaluation of Gauss-Legendre curves
-
Normal equations colorize Gaussian splats instantly
Instant Colorization of Gaussian Splats
-
Unsupervised distance evaluates noisy point cloud denoising
UGD: An Unsupervised Geometric Distance for Evaluating Real-world Noisy Point Cloud Denoising
-
IK-GAT is a graph-attention network that recovers full joint orientations from sparse 3D…
Amortized Inverse Kinematics via Graph Attention for Real-Time Human Avatar Animation
-
Phase and polarization control removes speckle in single-frame holograms
Ellipsography: Single-Shot Speckle-Free Holography via Vectorial Interference Shaping
-
MLPs inside each Gaussian capture high-frequency colors with fewer primitives
Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction
-
Dividing space and truncating displacements prevents penetrations
Divide and Truncate: A Penetration and Inversion Free Framework for Coupled Multi-physics Systems
-
Attribute tokens enable precise multi-factor lighting control in photos
TokenLight: Precise Lighting Control in Images using Attribute Tokens
-
Hybrid latents cut Gaussian primitives by 10x while raising view quality
Hybrid Latents: Geometry-Appearance-Aware Surfel Splatting
-
B-Rep topology alone yields stable part partitions for any CAD mesh
STEP-Parts: Geometric Partitioning of Boundary Representations for Large-Scale CAD Processing
-
Dual greedy method simplifies convex hulls to any size in O(n log n)
Progressive Convex Hull Simplification
-
Five problems organize all feed-forward 3D models
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
-
RL steers diffusion noise for fast character control
NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control
-
Adaptive depth map accelerates neural implicit surface sampling
SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces
-
ANVIL creates analogy animations rated adequate by educators
ANVIL: Analogies and Videos for Lecturers
-
Medial axis modeling improves global SDF accuracy from point clouds
Medial Axis Aware Learning of Signed Distance Functions
-
One flow model unifies motion generation
A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting
-
Multispectral 3DGS lifts quality on translucent scenes
MSGS: Multispectral 3D Gaussian Splatting
-
Four-part reflectance split improves novel-light 3D relighting
SSD-GS: Scattering and Shadow Decomposition for Relightable 3D Gaussian Splatting
-
Counterfactual edits cut shortcut learning in TCR binding models
Counterfactual Peptide Editing for Causal TCR--pMHC Binding Inference
-
Conformal abstention cuts TCR-pMHC errors from 18.7% to 10.9% at 80% coverage
Calibrated Abstention for Reliable TCR--pMHC Binding Prediction under Epitope Shift
-
Parallel voxelizer plus SGGX clustering improves microgeometry LoD accuracy
Fast Voxelization and Level of Detail for Microgeometry Rendering
-
New dataset shows markerless MoCap models struggle with real-world occlusions
A Dataset and Evaluation for Complex 4D Markerless Human Motion Capture