archive
Every paper Pith has read. Search by title, abstract, or pith.
456 papers in cs.GR · page 2
-
Single image becomes physics-based video via reused flow model
3DPhysVideo: Consistency-Guided Flow SDE for Video Generation via 3D Scene Reconstruction and Physical Simulation
-
Multi-agent loop lifts brand video yield to 89%
Genflow Ad Studio: A Compound AI Architecture for Brand-Aligned, Self-Correcting Video Generation
-
Multiple methods achieve ordered any-hit traversal in RTX
Ordered Front-to-back Any-Hit Traversal in RTX
-
Users adapt line chart simplifications by dataset
Beyond One-Size-Fits-All: User Strategies for Simplification Technique and Level Selection in Responsive Line Charts
-
AR test framework tracks stable areas in videos for 55.8% coverage
TARIPlay: A Test Framework for AR Applications based on Interactive Area Tracking in Playback Videos
-
Automated metrics replace human judgment for design videos
Evaluating Design Video Generation: Metrics for Compositional Fidelity
-
Gaussian splatting gets quota control for exact point counts
Smart target point control for Gaussian Splatting methods
-
Consensus ADMM distributes ABD simulations across nodes
Distributed Affine Body Dynamics with Adaptive Consensus
-
One diffusion checkpoint stipples any density at fixed cost
StippleDiffusion: Capacity-Constrained Stippling using Controlled Diffusion
2 Piths -
DealMaTe transfers materials using depth
DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer
-
Greedy proxy selects 25 panoramic views per scene while preserving coverage
CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage
-
Local 2D cues turn character videos into human performances
AnyAct: Towards Human Reenactment of Character Motion From Video
-
Sparse cues turn any character video into human motion
AnyAct: Towards Human Reenactment of Character Motion From Video
-
Safety layer blocks unsafe NSFW edits in 3D Gaussian Splatting
3DEditSafe: Defending 3D Editing Pipelines from Unsafe Generation
-
Medial axis of offset volume yields UDF meshes
OffsetAxis: UDF Mesh Reconstruction via Offset-Volume Medial Axis Extraction
-
Feature-space sampling speeds up 3D equivariant networks
Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space
-
Feed-forward model builds animatable head avatars from few photos in seconds
FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction
-
Audio and text tuning enables motion edits in video models
Sound Sparks Motion: Audio and Text Tuning for Video Editing
-
One transformer simulates cloth
WorldParticle: Unified World Simulation of Lagrangian Particle Dynamics via Transformer
-
One transformer unifies simulation across six physics types
WorldParticle: Unified World Simulation of Lagrangian Particle Dynamics via Transformer
-
Meschers process impossible objects without cuts or bends
Meschers: Geometry Processing of Impossible Objects
-
Sparse anchors steer motion synthesis with dual generation and refinement
AnchorRoute: Human Motion Synthesis with Interval-Routed Sparse Contro
-
TOPOS locks single-image 3D heads to fixed studio topology
TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation
-
Unified GPU solver gives exact gradients for stiff heterogeneous soft bodies
DiffPhD: A Unified Differentiable Solver for Projective Heterogeneous Materials in Elastodynamics with Contact-Rich GPU-Acceleration
-
3D scene edits yield consistent supervision for removal tasks
SceneForge: Structured World Supervision from 3D Interventions
-
Delta Forcing steers video generators to stay consistent after events
Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation
-
Delta Forcing curbs drift in interactive video generation
Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation
-
Trust region limits teacher bias in autoregressive video generation
Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation
-
Generative models automate social doing
Synthetic Sociality: How Generative Models Privatize the Social Fabric
-
Multi-term error metric simplifies noisy meshes faster
Fast and Robust Mesh Simplification for Generated and Real-World 3D Assets
-
Rectification offset aligns meshes for video 3D animation
R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
-
Rectification offset aligns mismatched meshes for video 4D animation
R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
-
BlitzGS is a distributed 3D Gaussian Splatting system that shards Gaussians by index…
BlitzGS: City-Scale Gaussian Splatting at Lightning Speed
-
Hierarchical transformer preconditioner reaches 21 fps on stiff Poisson systems
Hierarchical Transformer Preconditioning for Interactive Physics Simulation
-
Transformer preconditioner speeds stiff physics 28x
Hierarchical Transformer Preconditioning for Interactive Physics Simulation
-
Hypernetwork LoRA adds style to text-to-motion diffusion
Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
-
Coupled latents produce 3D assets with built-in skeletons and skinning
Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation
-
Diffusion over implicit reps generates motions from sparse keyframes
Generative Motion In-betweening by Diffusion over Continuous Implicit Representations
-
Groups modeled as dynamical systems via behavioral fields
BEHAVE: A Hybrid AI Framework for Real-Time Modeling of Collective Human Dynamics
-
Forearm guidance recovers absolute 3D hands from one egocentric camera
EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera
-
Structured traces lift algorithm video success to 99.8%
ALGOGEN: Tool-Generated Verifiable Traces for Reliable Algorithm Visualization
-
Diffusion stages progress from geometry to appearance
MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics
-
MoCam improves novel view synthesis on flawed point clouds
MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics
-
WildRelight dataset adapts synthetic relighting models to real scenes on the fly
WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting
1 Piths -
Streaming assembly matches full rebuilds exactly in tetrahedral simulations
STA-FEM: Exact Streaming Assembly for Preplanned Dynamic Tetrahedral Topology Edits
-
Shift mapping makes ToF reservoir resampling interactive
ToF ReSTIR: Time-of-Flight Rendering with Spatio-temporal Reservoir Resampling
-
Low-resolution 3DGS yields high-res high-frame-rate video
3DGS$^3$: Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering
-
Physics simulation steers 3D Gaussian splatting to functional shapes
PG-3DGS: Optimizing 3D Gaussian Splatting to Satisfy Physics Objectives
-
One latent scene maps to full HDR exposure stack in single pass
LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDR
-
Inverted culling speeds dynamic LiDAR ray tracing
Geometrically Approximated Modeling for Emitter-Centric Ray-Triangle Filtering in Arbitrarily Dynamic LiDAR Simulation