4 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
WorldSR is a novel framework that augments SR with explicit, entity-aligned visual world knowledge and suggests that entity-level grounding in external visual world knowledge provides a simple and effective complement to model-bound generative priors.
This work presents ClearGS for 3D Gaussian Splatting (3DGS), which achieves state-of-the-art overall performance, with consistent CLIP-IQA and MUSIQ gains and LPIPS reductions in most degradation settings, without paired sharp supervision or matched clean references.
Spackle is a lightweight residual learning framework that mitigates capacity competition without sacrificing efficiency on large-view-deviation NVS cases and achieves state-of-the-art performance on large-view-deviation cases.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
