[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

🌐 3D and 4D World Modeling: A Survey

Medical image processing in Python

ICCV 2025 | TesserAct: Learning 4D Embodied World Models

[NeurIPS 2024] Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models

Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions (RAL 2022)

physical optics: integrated modeling, phase retrieval, segmented systems, polynomials and fitting, sequential raytracing...

Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation

[CVPR'25] Official PyTorch implementation of AvatarArtist: Open-Domain 4D Avatarization.

A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.

[ICCV 2025] Official code for AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation

"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency", Yuyang Yin*, Dejia Xu*, Zhangyang Wang, Yao Zhao, Yunchao Wei

🔥 Motion Anything: Any to Motion Generation

This is the official implementation of Tensor4D: Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering.

Official implementation of Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion

TC4D: Trajectory-Conditioned Text-to-4D Generation

[CVPR 2026] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

[ICLR 2026] Light-X: Generative 4D Video Rendering with Camera and Illumination Control

🌐 Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems

[CVPR 2026] MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE

Modern, beginner-friendly 3D and 4D Rubik's cube simulator

[ICCV 2025] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

Scalable Optical Flow-based Image Montaging and Alignment

[NeurIPS 2025] Official code for Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos

[CVPR 2026] Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models.

Revealing Occlusions with 4D Neural Fields (CVPR 2022 Oral) - Official Implementation

"Comp4D: Compositional 4D Scene Generation", Dejia Xu*, Hanwen Liang*, Neel P. Bhatt, Hezhen Hu, Hanxue Liang, Konstantinos N. Plataniotis, and Zhangyang Wang

Node4D and other 4-dimensional types for making 4D games in Godot.

Curved Space Shader in Three.js (via 4D sphere projection)

Ray4 is a 4D raytracer original developed for my 1991 master's thesis in computer science