BestHub
Sign in
Machine Heart
Machine Heart
Apr 10, 2026 · Artificial Intelligence

Ant AI Wins CVPR 2026 Challenge: A Powerful Countermeasure Against Deepfake Abuse

Amid rising deep‑fake misuse in entertainment, Ant Group’s AI Security Lab won the CVPR 2026 NTIRE Robust AIGC Image Detection challenge with a ROC AUC of 0.9723, presenting a DINOv3‑based robust detection framework, extensive multi‑source data, and novel augmentation and optimization techniques to combat AI‑generated abuse.

AIGCCVPR 2026DINOv3
0 likes · 10 min read
Ant AI Wins CVPR 2026 Challenge: A Powerful Countermeasure Against Deepfake Abuse
AI Frontier Lectures
AI Frontier Lectures
Nov 25, 2025 · Artificial Intelligence

How RoMa v2 Achieves Harder, Better, Faster, Denser Feature Matching

RoMa v2 introduces a two‑stage matching‑then‑refinement pipeline powered by DINOv3 features, custom CUDA kernels, and diverse training data, delivering state‑of‑the‑art accuracy, speed, and pixel‑level uncertainty estimation across a wide range of dense matching benchmarks.

DINOv3RoMa v2benchmark results
0 likes · 10 min read
How RoMa v2 Achieves Harder, Better, Faster, Denser Feature Matching
AI Algorithm Path
AI Algorithm Path
Aug 16, 2025 · Artificial Intelligence

Meta Unveils DINOv3: A Universal Self‑Supervised Visual AI for All Image Tasks

Meta's DINOv3 is a 70‑billion‑parameter self‑supervised visual foundation model trained on 17 billion Instagram images without any labels, introducing dense feature extraction, Gram‑Anchoring to prevent feature collapse, high‑resolution adaptation, and multi‑student distillation that together enable out‑of‑the‑box performance on segmentation, depth estimation, 3D matching, and tracking while surpassing prior models such as DINOv2, CLIP, and SAM.

DINOv3Gram AnchoringLarge-Scale Training
0 likes · 8 min read
Meta Unveils DINOv3: A Universal Self‑Supervised Visual AI for All Image Tasks