ByteDance: Depth Anything V2

SAM 3D Objects is a 3D reconstruction model released on November 19, 2025 by Meta AI as part of the broader SAM 3 release. It extends the Segment Anything Model family from 2D segmentation into 3D object reconstruction, predicting geometry, texture, and spatial layout for individual objects from a single RGB image. Given an image together with a prompt identifying the object (a segmentation mask, point, or bounding box), the model outputs a full textured 3D mesh, without requiring multi-view captures, depth sensors, or known camera parameters.SAM 3D Objects uses a two-stage transformer architecture: a coarse stage that predicts 3D shape and object pose, followed by a refinement stage that adds texture and surface detail, with DINOv2 used to encode the input image. The model is trained via a human-and-model-in-the-loop data engine that combines synthetic 3D assets with real-image annotations, producing approximately 3.14 million mesh annotations across nearly 1 million images. Meta released SAM 3D Objects alongside SAM 3D Body, a companion model for single-image human mesh recovery, and SAM 3D Artist Objects (SA-3DAO), a new evaluation benchmark assembled with artist-created 3D ground truth. The model is designed as a companion to SAM 3 for downstream applications including augmented reality, robotics, content creation, and visual effects; it already powers the View in Room feature on Facebook Marketplace. SAM 3D Objects is released under the SAM 3 license; users should review the license terms prior to commercial use.

DINOv2 is a self-supervised vision foundation model released in April 2023 by Meta AI's FAIR lab. It produces general-purpose visual features that transfer to a wide range of downstream tasks (including image classification, semantic segmentation, depth estimation, and image retrieval) without requiring task-specific fine-tuning. DINOv2 is trained on a curated dataset of 142 million images using a self-supervised objective combining student-teacher distillation, masked image modeling, and an image-level contrastive loss, extending the approach introduced in the original DINO.The model family spans Vision Transformer sizes from ViT-S (21M parameters) to ViT-g (1.1B parameters), with the larger variants setting state-of-the-art results on linear-probing benchmarks for classification, segmentation, and dense prediction tasks at release. DINOv2 features can be used directly as frozen backbones, reducing the need for labeled training data in downstream applications. The model is primarily used as an image encoder rather than as a complete task-specific model, making it a common backbone choice for custom vision pipelines. DINOv2 code and pretrained weights are released under the Apache 2.0 license, which was adopted after an initial CC-BY-NC 4.0 release in response to community requests for commercial compatibility. A successor model, DINOv3, was released in August 2025 with further scaling and a new training technique called Gram anchoring.