Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

ConvStack

ConvStack is a convolutional decoder architecture, termed ConvStack, which is more appropriate for dense geometric reconstruction.1 The decoder follows a pyramid structure composed of a shared convolutional neck and multiple task-specific heads.2

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. we adopt a convolutional decoder architecture, termed ConvStack, which is more appropriate for dense geometric reconstruction — Masked Depth Modeling for Spatial Perception
  2. The decoder follows a pyramid structure composed of a shared convolutional neck and multiple task-specific heads — Masked Depth Modeling for Spatial Perception

Filed under model architecture › multimodal architecture