Applied & Human-Centered · Computer Science & AI
Graphics
The newest papers in Graphics that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
278 papers, from 31 August 2026 to 5 November 2026: 265 arXiv preprints and 13 OpenAlex records.
Get the few papers worth your time in Graphics every morning.
Follow Graphics and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 7
RiCo: Neural Simulation of Rigid-Body Interactions via Local Contact Reasoning
Accurate simulation of rigid-body interactions is essential for predictive physical world models.SpaceFlow: Locally Controllable 3D Generation
Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control strength, and appearance cannot be specified locally.BrickBench: Evaluating Agentic Brick Design
We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design.OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs
Recent 3D world models generate photorealistic, explorable scenes that remain frozen in time.PriMoRetarget: Humanoid Motion Transfer Through Prioritized Motion Retargeting
Motion retargeting is a critical preprocessing step for transferring human motion data to humanoid robots.From Prototype to Massing: Learning Graph Correspondence for Scalable Facade Modeling
Facade articulation at building scale is usually resolved manually or through parametric systems that encode design intent as explicit rules.Co${}^{2}$Skill: Whole-Body Control via Skill Composition for Long-Horizon Human-Environment Interaction
Achieving human-level dexterity in complex, unstructured environments requires the seamless integration of whole-body scene interaction and dexterous object manipulation skills.emg2face: Expressive Facial Animation with High-Density Surface EMG
Facial movements convey subtle and important information that is critical for human social communication.ScribbleEdit: A Benchmark for Scribble-Only Image Editing
Scribble-based interaction provides a lightweight and intuitive way for users to specify image editing intents in interactive editing tools.KASALv2: Fully Automatic 3D Rotational Symmetry Classification and Axis Localization
Rotational symmetry is an important prior in 6D pose estimation, improving pose accuracy and supporting symmetry-aware evaluation.End-to-End Autonomous Generation of Human Assembly Plans
Turning a CAD design into an assembly plan is still largely done by hand, requiring engineers to reason about geometric feasibility, tool access, stability, and the ergonomics of human assembly.TRACK: Telemetry-Based Racing Analysis and Coaching Kit in Sim Racing Games
This paper presents TRACK (Telemetry-Based Racing Analysis and Coaching Kit), which is a framework for analyzing driving performance in sim racing and profiling how individual drivers behave behind…WorldBench: Evaluating LLMs on Three.js Voxel World Generation
Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable.Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training
We present Fluid-Gen-Zero, a training-free framework for physics-aware fluid-object interaction video generation that decouples physical reasoning from appearance synthesis.PCAsplat: Gaussian Splatting with Local PCA Regularization
Gaussian splatting has emerged as a flexible representation for 3D reconstruction from posed images.PhysLDM: Latent Diffusion for High-Fidelity Deformable Simulation
Neural simulation of high-fidelity deformable bodies is a foundational challenge in computer graphics and physical AI.UltraDiff: Differentiable Ray Tracing in Ultrasound for Shape Optimization
Physically-based differentiable rendering enables gradient-based optimization of scene parameters by matching rendered images to measurements, but has so far mainly focused on light transport.View Matters: Keyframe-Guided Text-Driven 3D Gaussian Editing
Text-driven 3D Gaussian editing commonly does not distinguish the editing reliability of rendered views, although different viewpoints provide supervision of substantially different quality.Humanoid Horizon: Extending Task Horizon in Whole-Body Loco-Manipulation via Parallel Training, Dynamic Starting, and Reward Gating
Cluttered indoor environments, where large and heavy objects are scattered across diverse surfaces, require humanoid robots to sequentially navigate, grasp, transport, and accurately place each item…PDB: Point-Based Deformation Blending for Facial Animation Retargeting
Mesh-agnostic facial animation retargeting transfers expressions across meshes with different structures, but preserving facial motion without surface artifacts remains challenging.