Product Information
Description
An annual survey of the cs.GR arXiv category, covering research published from September 2025 – August 2026. Built on a close-reading set of 100 papers and organised into 20 chapters, it maps the year by the field's research sub-directions.
Book framework (share of the year's output):
- Physics-Based Motion Control and Character Animation (77.0%) — Focuses on integrating physics simulation with learned motion priors to enable accurate, interactive, and long-horizon character control and animation.
- 3D Gaussian Splatting and Neural Scene Representation (22.7%) — Explores dynamic 3D Gaussian splatting techniques for efficient scene reconstruction, rendering, and editing in video and image synthesis pipelines.
- Compact Geometry Representation and Fine-Grained Editing (0.2%) — Addresses the challenge of representing and editing high-resolution 3D geometric structures using compact, fine-grained, and efficient architectures.
- Physics-Based Dexterous Hand Control (0.1%) — Investigates learning-based control pipelines for precise, muscle-driven dexterous hand manipulation within physics-based simulation environments.
Each sub-direction is covered across three chapters — how it framed its questions, the strength of its key findings, and its open debates and frontiers — so the reader gets a traceable picture of what this part of the field actually produced over the year.
