SCoPE: Sightline-Coordinate Positional Encoding for 3D-Aware Video Generation

Distill Minimax-H3 into 4 steps

repo for QuerySplat

MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold

Differentiable Voxelization of Surface Representations (SIGGRAPH 2026)

Office inference code for World Tracing (object/scene/dynamic). Live demos: https://haoz19.github.io/world-tracing-page/

The official implementation of SIGGRAPH Asia 2026 paper "ID-V2V: Identity-preserving Video Restylization"

An open ecosystem of parametric human models and perception stacks, starting with GNM Head.

Official implementation of UniWorld-View

[SIGGRAPH Asia 2026 Journal Track] InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

A Curated List of Awesome Video World Models with AR Diffusion: Covering Algorithms, Applications, and Infrastructure, Aimed at Serving as a Comprehensive Resource for Researchers, Practitioners, a…

Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory

Official codebase for "One-Forcing: Towards Stable One-Step Autoregressive Video Generation"

Infinite Interactive World Rollout on a Single Desktop GPU

Infinite Worlds with Versatile Interactions

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

A Roadmap to Build World Models for Robot Policy Evaluation

Box3D is a 3D physics engine for games

Implementation of Lift4d, Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild, from Litman et al. of Carnegie Mellon

Boogu-Image-0.1 is an Apache-2.0 open-source image generation and editing model family that delivers near-closed-source performance with an order of magnitude less data.

Laas: 3D world built by Claude Fable 5 to test its capabilities using three.js

Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning

[CVPR 2026] FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning

Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation

[CVPR 2026 Oral] Official implementation for ChordEdit: One-Step Low-Energy Transport for Image Editing

[CVPR 2026] Official code for BulletTime: Decoupled Control of Time and Camera Pose for Video Generation