Computer Vision
-
NVIDIA LocateAnything Predicts Bounding Boxes in Parallel, Not Token by Token
LocateAnything is an NVIDIA vision-language model built around a single bet: stop generating bounding-box coordinates one token at a time. Visual grounding — pointing a model at “the red mug behind the laptop” and getting back exact pixel coordinates — has typically been autoregressive, emitting each coordinate number in sequence. That’s slow, and the speed… Continue reading
-
TriSplat Exports Simulation-Ready 3D Meshes in Under 1.3 Seconds
TriSplat is a feed-forward network that reconstructs a 3D scene from sparse, unposed images and exports it as a simulation-ready triangle mesh — in a single forward pass. No camera calibration, no post-hoc mesh extraction step. ## Triangles instead of Gaussians Most recent reconstruction pipelines use Gaussian splatting, which renders beautifully but needs a slow,… Continue reading
