Masked Depth Modeling for Spatial Perception

[CVPR26 Highlight] RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations

An curated list for feed-forward 3D scene modeling, including research directions, datasets, and applications.

Project Lyra: Open Generative 3D World Models

A feed-forward 3D foundation model for reconstructing scenes from streaming data

[Preprint] Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale

A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related webs…

Generative World Renderer: an AI-native Renderer for Games and Virtual Worlds. 面向游戏与虚拟世界的AI原生渲染引擎

Unified Codebase for Advanced World Models.

Reimplementation of LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

Our method reconstructs 3D worlds from video diffusion models using non-rigid alignment to resolve inherent 3D inconsistencies in the generated sequences.

Geometry-grounded Point Transformer (CVPR 2026)

Advancing Open-source World Models

🌐 3D and 4D World Modeling: A Survey

[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny co…

[CVPR 2026] Implementation of paper "SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model"

CoWTracker: Tracking by Warping instead of Correlation

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

[CVPR 2026 Highlight] NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

[CVPR 2026] InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

Any4D: Unified Feed-Forward Metric 4D Reconstruction

Depth Anything 3

[CVPR'26 Highlight] AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend

MapAnything: Universal Feed-Forward Metric 3D Reconstruction