Datasets › SynMirror

SynMirror

Introduced by Ankit Dhiman et al. in Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections23 Sep 2024 archive 2025-07-28

SynMirror consists of samples rendered from 3D assets of two widely used 3D object datasets - Objaverse and Amazon Berkeley Objects (ABO) placed in front of a mirror in a virtual blender environment. The total number of rendered samples are $198,204$. Each rendering contains colors, category_id_segmaps, depth, normals and cam_states.

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

Papers archive 2025-07-28

No paper in the archive has a leaderboard row on this dataset; the archive counts 2 papers for it but never published that list.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

No task tagged in the archive.

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • SynMirror

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections