AI Paper Atlas

Research map / 3D vision / 3D generation

AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments

Xuzhi Wang, Xinran Wu, Song Wang, Lingdong Kong, Ziping Zhao

CVPR 2026 · 3D vision › 3D generation · approach: Semantic scene completion · 1 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
add Adaptive Serialized Attention (ablation)conv-only baseline · NYUv2 testSSC mIoU (%): 28.68 -> 30.98Improved
add Center-Relative Positional Encoding (ablation)baseline + ASA · NYUv2 testSSC mIoU (%): 30.98 -> 31.66Improved
add Conv-Modulated Layer Normalization block (ablation)baseline + ASA + CRPE · NYUv2 testSSC mIoU (%): 31.66 -> 32.50Improved
learn shifts with Gumbel-Softmax instead of direct discrete parameters (ablation)ASA · NYUv2 testSSC mIoU (%): 30.61 -> 31.96Improved
add temperature annealing to Gumbel-Softmax shift learning (ablation)ASA · NYUv2 testSSC mIoU (%): 31.96 -> 32.50Improved
use projected voxel mean as scene center instead of physical center (ablation)CRPE · NYUv2 testSSC mIoU (%): 32.11 -> 32.50Improved
add relative yaw and pitch positional encoding (ablation)CRPE · NYUv2 testSSC mIoU (%): 32.23 -> 32.50Improved
add ASA component (latency cost) (ablation)AdaSFormer · Latencylatency (ms): 156.0 -> 178.9Hurt
use AdaSFormer instead of ISOISO · Latencylatency (ms): 535.2 -> 178.9Improved
use AdaSFormer instead of ISO on Occ-ScanNetISO · Occ-ScanNet valmIoU (%): 28.71 -> 45.33Improved
use AdaSFormer instead of MonoMRN on NYUv2 scene completionMonoMRN · NYUv2 testSC IoU (%): 53.16 -> 51.33Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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