computer-vision 10
- Depth Anything 3: Recovering 3D Visual Space via Unified Depth-Ray Transformers
- VGGT: Visual Geometry Grounded Transformer for Feed-Forward 3D Reconstruction
- MultiPly Architecture: Multi-Person 3D Motion and Body Reconstruction
- FaceLift Architecture: Semi-Supervised 3D Facial Landmark Estimation
- GenWarp: Semantic-Preserving Generative Warping for Novel View Synthesis
- FoundationPose Architecture: Zero-Shot 6D Object Pose Estimation and Tracking
- ViViD: Video Virtual Try-On Using Diffusion Models and Temporal Attention
- Foundational AI Architectures: Mapping the Canonical Papers of Modern Deep Learning
- Diffusion Transformers (DiT): The Architectural Backbone of Sora and Video Generation
- WebGL to WebGPU: The Architectural Evolution of Real-Time Browser Graphics