aim-uofa

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.

[ICLR'24 & IJCV‘25] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

[ICLR'25] Official PyTorch implementation of "Framer: Interactive Frame Interpolation".

[ICLR'25] MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences

[NeurIPS 2025 Spotlight] A Generalist Diffusion Model for Vision Perception

[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

This is an unofficial PyTorch implementation of StyleDrop: Text-to-Image Generation in Any Style.

[ECCV 2022] The official repo for the paper "Poseur: Direct Human Pose Regression with Transformers".

[CVPR 2024] Official PyTorch implementation of FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition

One-shot and Few-shot 3D Editing without Per-Scene Optimization

[3DV 2026] Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting

[IJCV'24] AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort

[ICCV2023] 🧊FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models

[NeurIPS 2025] Official Repo of Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

[CVPR2025] SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

Official Implementation of ICCV 2023 Paper - SegPrompt: Boosting Open-World Segmentation via Category-level Prompt Learning

[SIGGRAPH2025] Generative Video Matting

More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning

[ICLR 2024] Official PyTorch/Diffusers implementation of "Object-aware Inversion and Reassembly for Image Editing"

[ICML2026] ACTIVE-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO

[NeurIPS'24] A Simple Image Segmentation Framework via In-Context Examples

[SIGGRAPH 2026] AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation

A toolbox for benchmarking SOTA discriminative and generative geometry estimation models.

[ICLR'26] Official PyTorch implementation of "Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models".

SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting

DiverGen (CVPR 2024) & BSGAL (ICML 2024)

[NeurIPS'24] Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation (Diffews)

[ACL'26] EvoToken-DLM (Beyond Hard Masks: Progressive Token Evolution for Diffusion Language)