S2R-Bench

What is S2R-Bench?

S2R-Bench evaluates video reflection removal, supporting full-reference and human perceptual assessment, and is used to validate the S2R-Removal model.

Released

2026-08-12

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/2608.11562

S2R-Bench paper

• Paper https://arxiv.org/abs/2608.11562
• Website https://codingwzp.github.io/VideoDereflection_S2R

Which sources cite S2R-Bench?

• S2R-Bench

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