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

[ACM TIST 2025] GenAI in Fashion: Overview, also includes 🔥latest papers, ⚙️metrics, 👀workshops, 🚀companies & products, ...)

Official Implementation of "Design2Cloth: 3D Cloth Generation from 2D Masks" (CVPR2024)

An intelligent fashion recommendation agent powered by image segmentation, multi-modal fusion, and large language models (LLMs).

Official repo for "IDArb: Intrinsic Decomposition for arbitrary number of input views and illuminations"

Quality of Life ComfyUI nodes from ControlAltAI.

Official implementation of "Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion" [CVPR2025]

Import Festivities' blender genshin shader into MMD model in one button

[ICLR 2025] Latent Radiance Fields with 3D-aware 2D Representations

Repo for the papers "Intrinsic Image Decomposition via Ordinal Shading" (TOG 2023) and "Colorful Diffuse Intrinsic Image Decomposition in the Wild" (TOG 2024)

[CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/

[CVPR 2025 Highlight] Material Anything: Generating Materials for Any 3D Object via Diffusion

Official implementation of PoNQ

Differentiable Rendering of Parametric Geometry (SIGGRAPH Asia 2023)

[NeurIPS 2024] Animate3D: Animating Any 3D Model with Multi-view Video Diffusion

MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR

https://liuar0512.github.io/part123_official_page/

[CVPR2024 (Highlight)] RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D. Live Demo：https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC

Official implementation for "DMesh: A Differentiable Representation for General Meshes" (NeurIPS 2024)

CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes

[NeurIPS 2024 Spotlight] Tetrahedron Splatting for 3D Generation

CraftsMan: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner

An official implementation of FlexiDreamer: Single Image-to-3D Generation with FlexiCubes.

some materials about mesh processing, including papers, videos, codes, and so on. Updating every day!

Transparent Image Layer Diffusion using Latent Transparency