AI Paper Atlas

Research map / 3D vision / 3D generation

Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing

Yajie Xing, Jingbo Wang, Gang Zeng

ECCV 2020 · 3D vision › 3D generation · approach: Semantic scene completion · 47 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
make a_k and t learnable instead of fixed (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 48.33 -> 48.62Improved
add learnable kernel rebalancing weights b_k (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 48.62 -> 48.80Improved
make only the kernel center a_k learnable (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 48.28 -> 48.33No clear effect
learn the depth receptive field versus fixing it (fixed vs full) (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 48.28 -> 48.80Improved
increase kernels from 1 to 3 (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 47.08 -> 48.80Improved
increase kernels from 3 to 5 (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 48.80 -> 48.17Hurt
initialize a_k with larger values [-4,-2,0,2,4] (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 48.80 -> 48.66Hurt
initialize a_k with smaller values [-1,-0.5,0,0.5,1] (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 48.80 -> 48.42Hurt
initialize t to 0.5 instead of 1 (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 48.80 -> 48.69Hurt
initialize t to 2 instead of 1 (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 48.80 -> 48.74Hurt
use malleable 2.5D conv in all of res2-res5 rather than res2,res3 only (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 48.27 -> 48.80Improved
use malleable 2.5D conv in res2-res5 rather than res3-res5 (ablation)Malleable 2.5D (3 kernels, ResNet-50) · NYUDv2mIoU (%): 48.58 -> 48.80Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy