ByteDance Vision Models

Compare both ByteDance vision models we track, all of them open-weight.

2 models · 2 open-weight · Updated Jun 2024

About ByteDance Vision Models

Every ByteDance vision model in our catalog is open-weight. Both publish downloadable weights, so you can self-host under their own licenses instead of paying per request. The open-weight side runs on Apache 2.0 and MIT licenses. The newest additions are Depth Anything V2 (Jun 2024) and ByteTrack (Oct 2021).

The ByteDance models we list cover depth estimation (1 model) and video object tracking (1).

On the open-weight tier, Depth Anything V2 runs at 25M to 1.3B parameters. Both carry a permissive license, so commercial use is straightforward.

With every model here open-weight, the real trade is size against generality: the smaller checkpoints fine-tune and deploy cheaply on your own hardware, while the larger ones cover more ground out of the box. Compare their licenses, sizes, prices, and release dates in the tables below, then open any model page for the full specification.

Which ByteDance Model Should You Use?

What each of the 2 ByteDance vision models in our catalog is built for, and how you run it.

Depth Anything V2: Best for: Depth Estimation. Open weights: Apache 2.0 license, 25M to 1.3B parameters. Self-host it or run it here. Small enough for on-device and edge deployment.
ByteTrack: Best for: Video Object Tracking. Open weights: MIT license. Self-host it or run it here.

Open-Source ByteDance Models

2 models with downloadable weights you can self-host under their licenses (Apache 2.0 and MIT).

Depth Anything V2

Depth Anything V2 is a monocular depth estimation model released in June 2024 by researchers at the University of Hong Kong and TikTok. It predicts a dense depth map from a single RGB image, enabling 3D-aware applications without the need for stereo cameras, LiDAR, or multi-view inputs. The model improves on the original Depth Anything through three modifications: replacing real labeled images with 595K high-quality synthetic images during teacher training, scaling up teacher model capacity, and using the stronger teacher to generate pseudo-labels on 62 million unlabeled real images used to train the student models. This pipeline reduces the depth prediction artifacts that can occur in reflective, transparent, and texture-poor regions. Compared to diffusion-based depth models such as Marigold, Depth Anything V2 runs more than 10× faster while producing more accurate predictions.Depth Anything V2 is released in four sizes: Small (25M), Base (97M), Large (335M), and Giant (1.3B), and in two output modes: relative depth (normalized scene-level estimates) and metric depth (absolute distance in meters, produced by fine-tuning the relative-depth backbone on depth-annotated datasets). The Small, Base, and Large model weights are released under Apache 2.0, and the Giant variant under CC-BY-NC-4.0 for non-commercial use. A successor model, Depth Anything 3, was released in November 2025 by the ByteDance Seed team, extending the framework to multi-view depth estimation and camera pose recovery.

ByteTrack

ByteTrack is a multi-object tracking algorithm developed by ByteDance, released in October 2021. It addresses a core limitation of earlier tracking methods by associating every detection box — not just high-confidence ones — with tracklets using a two-stage matching process. Low-score detection boxes, which typically correspond to occluded or blurry objects, are retained in a secondary matching step against unmatched tracklets, significantly reducing the number of lost tracks.ByteTrack achieves strong performance on the MOT17 and MOT20 benchmarks at the time of release, operating in real time on standard GPU hardware. It is architecture-agnostic and can be paired with any object detector, making it straightforward to integrate into existing detection pipelines for video analytics, surveillance, and sports tracking applications.

Frequently Asked Questions About ByteDance Vision Models

Which ByteDance models can do depth estimation?

1 of the 2 ByteDance vision models we track handles depth estimation: Depth Anything V2. Each model page lists its full task coverage, license, and specs.

Which ByteDance models can do video object tracking?

1 of the 2 ByteDance vision models we track handles video object tracking: ByteTrack. Each model page lists its full task coverage, license, and specs.

Are ByteDance vision models open source?

Yes. Both ByteDance vision models we track publish downloadable weights you can self-host under their licenses (Apache 2.0 and MIT).

How many ByteDance vision models are on Roboflow Playground?

We track 2 live ByteDance vision models. The most recent addition is Depth Anything V2, released Jun 2024.

This page lists both ByteDance vision models in the Roboflow Playground catalog, all of them open-weight and free to self-host. They cover depth estimation and video object tracking, among other tasks. Compare licenses, parameters, prices, and release dates side by side, or open any model page for full details.