[CVPR 2025] VGGT: Visual Geometry Grounded Transformer

[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

[ICLR 2025 Spotlight] Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation

Official implementation of "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"

DUSt3R: Geometric 3D Vision Made Easy

🐍 Geometric Computer Vision Library for Spatial AI

Official Pytorch Implementation for "SceneScape: Text-Driven Consistent Scene Generation"

A tiny, didactical implementation of LLAMA 3

[ACCV 2024] Official Implementation of "AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description". Junyu Xie, Tengda Han, Max Bain, Arsha Nagrani, Gül Varol, Weidi Xie, Andrew Zisserman

The Arcade Learning Environment (ALE) -- a platform for AI research.

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

[ICLR2025] Kolmogorov-Arnold Transformer

MambaOut: Do We Really Need Mamba for Vision? (CVPR 2025)

Official Implementation of Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics

🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors

[3DV 2025]🐱🐶🐲🐮🐷Official Implementation of DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

A pure pytorch implementation of 3D gaussian Splatting

Examples and exercises for B16 - Algorithms.

[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

News: the 10k dataset is ready for download.

[ICLR 2025] Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Rembg is a tool to remove images background