Autonomous GPU Kernel Generation via Deep Agents

Official implementation of "DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training".

🐻 Uniform Discrete Diffusion with Metric Path for Video Generation

A framework to convert any 2D videos to immersive stereoscopic 3D

Web-based 3D visualization + Python

[ICCV 2025] GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

[CVPR 2025 Highlight] DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

ICCV 2025 论文和开源项目合集

We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.

STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing

From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation

Monocular Depth Estimation Toolbox based on MMSegmentation.

Depth Any Video with Scalable Synthetic Data (ICLR 2025)

Arbitrary Length Video Using Frame Chunking Based on official repository of code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

[CVPR 2021] Self-supervised depth estimation from short sequences

Self-supervised temporally consistent depth estimation

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.

Enforcing Temporal Consistency in Video Depth Estimation, ICCV-W 2021.

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Open source implementation of "A Self-Supervised Descriptor for Image Copy Detection" (SSCD).

2021年最新总结，推荐工程师合适读本，计算机科学，软件技术，创业，思想类，数学类，人物传记书籍

Convert ONNX models to PyTorch.

RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization

Codes for "RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization"