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
As-Rigid-As- Possible Deformation of Gaussian Radiance Fields
Canonical reference. 95% of citing Pith papers cite this work as background.
58
Pith papers citing it
Background
95% of classified citations
hub tools
citation-role summary
background 21
citation-polarity summary
roles
background 21representative citing papers
Introduces the first algorithmic framework for responsive thematic mapping via layout guides that encode map element sizes and relative positions, demonstrated on rectangular and Demers cartograms.
FLUIDSPLAT models flow fields with K anisotropic Gaussian primitives, proves an O(K^{-s/d}) approximation rate under Sobolev smoothness s, derives optimal K scaling with N sensors, and reports 11-28% error reduction on four flow benchmarks.
Vega-Video integrates video into Vega via synchronization, annotation, and transformation classes, using split signals and VOD repurposing for responsive mixed-modality visualizations.
Proteus uses a multi-level design space and LLM multi-agents to automatically convert desktop visualizations into equivalent mobile versions that preserve readability.
A survey of 55 agentic VA systems proposes a co-evolutionary framework defining four agent roles (PLANNER, CREATOR, REVIEWER, CONTEXT MANAGER) mapped to visual analytics pipeline stages along with design guidelines.
Literate execution treats documentation and visualizations as dynamic, computable parts of program execution via provenance tracking, inverting traditional literate programming to make programs more explorable.
Raiven mediates LLM visualization authoring via a formally defined DSL that unifies scientific and information visualization, producing deterministic, verifiable code from metadata-only inputs.
Presents a new retrieval system that enriches user queries with an intent taxonomy to improve matching of natural language descriptions to infographic designs and support authoring.
GS-Surrogate creates a canonical Gaussian field that is sequentially deformed by simulation parameters to enable real-time, controllable 3D exploration of ensemble data while separating simulation variations from visualization adjustments.
SwEYEpinch uses gaze swiping plus a held pinch gesture to reach 64.7 WPM in XR text entry after practice, outperforming sequential key selection and prior gaze-swipe methods in user studies.
SASAV introduces the first fully autonomous multi-agent system for scientific data analysis and visualization that operates without external prompting or human-in-the-loop feedback.
Semi-structured interviews with 15 visualization practitioners identify three emotion functions for viewers, three design facets, ethical considerations, and observations that affective intent often emerges during the process.
Episodic framing of text in mass shooting data visualizations elicits more negative emotions than thematic framing and indirectly increases support for gun control policies.
High-dimensional graph embeddings are projected to 2D views optimized for aesthetic metrics using a differentiable edge-crossing surrogate, outperforming standard layouts in tests.
Introduces a benchmark for MLLM-based chart data extraction from unlabeled images and a human-centered training framework that reaches SOTA numerical accuracy with a 7B model.
CAPE produces spatially grounded natural-language explanations for document layouts using pattern detection and multi-level context, rated more helpful than content-only baselines in a user study.
The paper introduces a channels-and-substrates framework grounded in distributed cognition to model interaction for ubiquitous and cross-device analytics.
MS-COOT uses co-optimal transport on hypergraph representations of Morse-Smale complexes to enable explicit region-to-region matching for identifying structural events such as splitting and merging.
Agentic iteration improves perceived quality of generated multiview genomics visualizations over direct LLM generation, but adding more specialist agents or a reviewer yields no further gains across 159 test cases.
AI peer review systems are vulnerable to prompt injections, prestige biases, assertion strength effects, and contextual poisoning, as demonstrated by a new attack taxonomy and causal experiments on real conference submissions.
GFlowState introduces interactive visualizations such as trajectory node-link diagrams and transition heatmaps to make GFlowNet training dynamics observable for debugging and quality assessment.
EdgeFormer converts point cloud edge detection into local-patch point classification with a transformer and reports competitive results against six baselines.
A web system uses a Curve Segment Neighborhood Graph to support interactive community detection, force-directed layouts, and adjacency matrix views for exploring hundreds of thousands of streamlines in real time.
citing papers explorer
-
Literate Execution
Literate execution treats documentation and visualizations as dynamic, computable parts of program execution via provenance tracking, inverting traditional literate programming to make programs more explorable.