RDVSv2 Benchmark

What is RDVSv2?

RDVSv2 is a large-scale benchmark for RGB-D video salient object detection, containing 249 video sequences with 29,077 annotated frames. It includes depth…

Released

2026-07-28

Evaluates

General AI, Vision & 3D, cs.CV

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.25392

RDVSv2 paper and code

• Paper https://arxiv.org/abs/2607.25392
• Code https://github.com/ltynick/RDVSv2

Which sources cite RDVSv2?

• RDVSv2

Related General AI, Vision & 3D, cs.CV benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 360CityArena
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench