MedianGS
PulseAugur coverage of MedianGS — every cluster mentioning MedianGS across labs, papers, and developer communities, ranked by signal.
-
New benchmark evaluates 3D consistency in text-to-video models
Researchers have introduced GeoT2V-Bench, a new benchmark designed to evaluate the 3D consistency of text-to-video (T2V) models. This benchmark assesses whether the video outputs from T2V models can support accurate 3D …
-
New Arko-T Model Generates Editable 3D Designs from Text
Researchers have developed Arko-T, a 4-billion parameter foundation model capable of generating executable CAD programs from natural language descriptions. This model focuses on creating editable, parametric designs rat…
-
OrbitForge generates 3D scenes from text via video synthesis and Gaussian Splatting
Researchers have developed OrbitForge, a new method for generating 3D scenes from text prompts by leveraging text-to-video models and Gaussian Splatting. OrbitForge converts a text-generated video into a consistent 3D s…