wovepaper — the arXiv observatory

The paper introduces Temporal Prior Decoupling (TPD), a training‑free method that restores suppressed late‑segment information during diffusion sampling for text‑to‑video models, i…

Publications (63)

GaNI: Global and Near Field Illumination Aware Neural Inverse Rendering

NARVis: Neural Accelerated Rendering for Real-Time Scientific Point Cloud Visualization

How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings

Improving the Perceptual Quality of 2D Animation Interpolation

Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces

TPD: Temporal Prior Decoupling for Text-to-Video Diffusion Models

SketchSplat: 3D Edge Reconstruction via Differentiable Multi-view Sketch Splatting

ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences

Temporally Consistent Motion Segmentation from RGB-D Video

Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives

LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents

3DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention

Improved Modeling of 3D Shapes with Multi-view Depth Maps

Inverse Global Illumination using a Neural Radiometric Prior

Rotated Lights for Consistent and Efficient 2D Gaussians Inverse Rendering

Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentions

3D Shape Completion with Multi-view Consistent Inference

Learning to Take Directions One Step at a Time

Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network

SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates

Neural Radiosity

Image Restoration using Autoencoding Priors

Challenges in Disentangling Independent Factors of Variation

DCR: Counterfactual Attractor Guidance for Rare Compositional Generation

L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention

Differentiable Neural Radiosity

SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization

Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views

PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters

Deep Mean-Shift Priors for Image Restoration

Transfer Learning for Pose Estimation of Illustrated Characters

DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Images

Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction

EgoRenderer: Rendering Human Avatars from Egocentric Camera Images

Learning to Importance Sample in Primary Sample Space

PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting

Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views

Y^2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences

HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars

PatchGame: Learning to Signal Mid-level Patches in Referential Games

Learning Generative Models using Denoising Density Estimators

View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions

ORCSolver: An Efficient Solver for Adaptive GUI Layout with OR-Constraints

FaceShop: Deep Sketch-based Face Image Editing

LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts

Generative Detail Enhancement for Physically Based Materials

SpeeDe3DGS: Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and Motion Grouping

Render4Completion: Synthesizing Multi-View Depth Maps for 3D Shape Completion

Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching

Bifurcation Analysis of Reaction Diffusion Systems on Arbitrary Surfaces

OmnimatteRF: Robust Omnimatte with 3D Background Modeling

Surface Reconstruction from Point Clouds by Learning Predictive Context Priors

Compositional Neural Textures

GLOW: Global Illumination-Aware Inverse Rendering of Indoor Scenes Captured with Dynamic Co-Located Light & Camera

Accelerated, Memory-Efficient Far-Field Scattering Computation with Monte Carlo SBR

Smart, Deep Copy-Paste

Continuous Curve Textures

SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation

Specular-to-Diffuse Translation for Multi-View Reconstruction

Disentangling Factors of Variation by Mixing Them

Learning to Generate Dense Point Clouds with Textures on Multiple Categories

SplatSuRe: Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splatting

Understanding the (un)interpretability of natural image distributions using generative models