# SurfConv: Bridging 3D and 2D Convolution for RGBD Images Source: [SurfConv: Bridging 3D and 2D Convolution for RGBD Images]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:18:52.954Z Authors: Hang Chu, Wei-Chiu Ma, Kaustav Kundu, Raquel Urtasun, Sanja Fidler Published: 2018-12-04T16:42:29.000Z ## Abstract We tackle the problem of using 3D information in convolutional neural networks for down-stream recognition tasks. Using depth as an additional channel alongside the RGB input has the scale variance problem present in image convolution based approaches. On the other hand, 3D convolution wastes a large amount of memory on mostly unoccupied 3D space, which consists of only the surface visible to the sensor. Instead, we propose SurfConv, which "slides" compact 2D filters along the visible 3D surface. SurfConv is formulated as a simple depth-aware multi-scale 2D convolution, through a new Data-Driven Depth Discretization (D4) scheme. We demonstrate the effectiveness of our method on indoor and outdoor 3D semantic segmentation datasets. Our method achieves state-of-the-art performance with less than 30% parameters used by the 3D convolution-based approaches. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Semantic Segmentation on KITTI (test)](): Semantic segmentation; KITTI (test); mIoU: 35.1. - [Semantic Segmentation on NYU v2 (test)](): Semantic segmentation; NYU v2 (test); mIoU: 31. ## Original sources and implementation [Original paper]() [PDF]()