Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
RenderBench: Benchmarking Render-to-Real Video Transfer with Reconstructed Digital Twins
Dicong Qiu, Zhiyuan Xu, Yaosheng Liu +2
Modern video models can generate realistic videos from real appearance references and proxy renders that specify scene structure, viewpoint changes, and motion. Evaluating this ren…
cs.CV2025
SD-OVON: A Semantics-aware Dataset and Benchmark Generation Pipeline for Open-Vocabulary Object Navigation in Dynamic Scenes
Dicong Qiu, Jiadi You, Zeying Gong +3
We present the Semantics-aware Dataset and Benchmark Generation Pipeline for Open-vocabulary Object Navigation in Dynamic Scenes (SD-OVON). It utilizes pretraining multimodal found…