Efficiently Reconstructing Dynamic Scenes One D4RT at a Time Paper • 2512.08924 • Published Dec 9, 2025 • 16
DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21, 2025 • 474
TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting Paper • 2503.17032 • Published Mar 21, 2025 • 27
DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding Paper • 2411.19527 • Published Nov 29, 2024 • 11
view article Article 🧨 Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e +6 Oct 3, 2023 • 9
ImagenHub: Standardizing the evaluation of conditional image generation models Paper • 2310.01596 • Published Oct 2, 2023 • 19
MagiCapture: High-Resolution Multi-Concept Portrait Customization Paper • 2309.06895 • Published Sep 13, 2023 • 27