ARGO Vision published a repository under Apache 2.0 for pseudo-instance supervision derived from motion boundaries.
Public source
Publisher name
Public post
👻👻Emerging Objects from Motion👻👻 👉Motion boundaries provide a strong signal for object-level grouping and can be used to derive pseudo-instance supervision. This ke…
Company
ARGO Vision
We See the Future | No Magic.
- Industry
- IT System Custom Software Development
- Location
- Milan, IT
- Company size
- 11–50 employees
About ARGO Vision
ARGO Vision is an innovative startup, born in 2016, that excels in computer vision and machine learning. We design innovative AI based solutions, empowering the companies' business worldwide. The founder: https://www.linkedin.com/in/visionarynet
See moreLatest activity
Latest activity from ARGO Vision
4 signals
Research & Knowledge
ARGO Vision announced that Weather-Conditioned Depth Anything from Texas A&M is the new SOTA in weather-robust depth estimation.
Research & Knowledge
ARGO Vision released a novel video dataset named Doppio capturing video of falling ground coffee with precise, per-frame ground-truth weight measurements.
Research & Knowledge
ARGO Vision published a unified segmentation and retrieval model called FoundYou, which segments the same physical instance in a new image or retrieves it from a large gallery with only one super-compact model.
Discover more
Similar signals
Similar public activity from other companies.
Research & Knowledge
Motional
Motional announced the release of the nuReasoning dataset and the launch of the nuReasoning Challenge at ECCV26.
Research & Knowledge
viso.ai
viso.ai published a video by Gaudenz Boesch explaining how VGI opens up new possibilities for understanding the physical world beyond predefined detections and rigid models.
Research & Knowledge
DNEG
DNEG published a code repository titled Point2Pose: 6D Object Tracking That Survives Total Occlusion.
Research & Knowledge
Visage Technologies
Visage Technologies published an article based on insights from its white paper on dataset insufficiencies in ADAS, examining gaps at different stages of the dataset lifecycle.
Research & Knowledge
Fast Code AI