Table of contents
- (논문 요약) DIFFUSION MODELS ARE REAL-TIME GAME ENGINES
- (논문 요약) DINOv3
- (논문 요약) Florence-2; Advancing a Unified Representation for a Variety of Vision Tasks
- (논문 요약) Generating Diverse High-Fidelity Images with VQ-VAE-2
- (논문 요약) LOTUS; Diffusion-based Visual Foundation Model for High-quality Dense Prediction
- (논문 요약) LeJEPA; Provable and Scalable Self-Supervised Learning Without the Heuristics
- (논문 요약) Movie Gen; A Cast of Media Foundation Models
- (논문 요약) Neural Discrete Representation Learning
- (논문 요약) Next-Embedding Prediction Makes Strong Vision Learners
- (논문 요약) Perception Encoder; The best visual embeddings are not at the output of the network
- (논문 요약) SAM 2; Segment Anything in Images and Videos
- (논문 요약) SAM 3D; 3Dfy Anything in Images
- (논문 요약) Segment Anything
- (논문 요약) Stretching Each Dollar; Diffusion Training from Scratch on a Micro-Budget
- Rotation matrix with Quaternion
- Top-view perspective transform with OpenCV-Python with OpenCV-Python
- Undistort Image with OpenCV-Python
- Visualize Pointcloud with Open3D