Mobile Shell

[ICLR 26] 1K resolution vision transformers pretrained on 1B human images.

TIPSv2 (CVPR'26) and TIPS (ICLR'25)

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

[SIGGRAPH‘2026] PEAR :Pixel-aligned Expressive humAn mesh Recovery

(ICLR2026) ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation

[SIGGRAPH 2026] AniGen: Unified S^3 Fields for Animatable 3D Asset Generation

[CVPR 2026] Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction

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

[3DV 2026] "SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass"

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D

FNIN: A Fourier Neural Operator-based Numerical Integration Network for Surface-form-gradients

[WACV 2026] Code for "Towards Fast and Scalable Normal Integration using Continuous Components"

Code for 'Discontinuity-aware Normal Integration for Generic Central Camera Models'

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

Official code for "LagerNVS Latent Geometry for Fully Neural Real-time Novel View Synthesis" (CVPR 2026)

SegviGen: Repurposing 3D Generative Model for Part Segmentation

SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation

[CVPR 2026] Physical Simulator In-the-Loop Video Generation

🎬ActionMesh: A fast video to animated mesh model with unprecedented quality. Generate animated mesh seamlessly importable into any 3D software in less than a minute.

[CVPR 2026] Official Code for "UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders"

[CVPR'26] Official implementation of "Emergent Outlier View Rejection in Visual Geometry Grounded Transformers"

[WACV 2026] Official implementation of "Edge-Aware Image Manipulation via Diffusion Models with a Novel Structure-Preservation Loss"

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

[ICLR 2026] PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Data

[ICLR 2026] FastVGGT: Fast Visual Geometry Transformer

SVRecon: Sparse Voxel Rasterization for Surface Reconstruction

VideoGPA is a self-supervised framework that enhances 3D consistency in Video Diffusion Models.