[AAAI 2026] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding. Accepted to ICLR 2026.

Reference PyTorch implementation and models for DINOv3

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

[AAAI 2026] Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices

Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"

[ICLR 2026] ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

[NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understanding

[NeurIPS 2025] Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

The repository for CVPR 2022 Paper "Neural 3D Video Synthesis"

Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Generating TDOM via 3DGS

[ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers

A Modular Framework for 3D Generation and Beyond [WIP]

Instead of removing dynamic objects as distractors and reconstructing only static environments, this paper proposes an efficient architecture that incrementally tracks camera poses and establishes …

[ICCV 2025, Oral] TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

A pure pytorch implementation of 3D gaussian Splatting

Reproducing Gaussian Splatting

Understand Human Behavior to Align True Needs

[CVPR 2025] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding

[CVPR 2025 Highlight] Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

[CVPR 2025] Prompt Depth Anything

LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors

[ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

3D Reconstruction for all