AI Paper Atlas

Research map / 3D vision / 3D generation

Unleashing Semantic and Geometric Priors for 3D Scene Completion

Shiyuan Chen, Wei Sui, Bohao Zhang, Zeyd Boukhers, John See, Cong Yang

AAAI 2026 · 3D vision › 3D generation · approach: Semantic scene completion · 4 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
replace baseline encoder with frozen Foundation Encoder (ablation)simplified CGFormer baseline · SemanticKITTI valmIoU: 16.53 -> 18.59Improved
add Geometry-Aware Context Adapter (ablation)FoundationSSC (FE only) · SemanticKITTI valmIoU: 18.59 -> 18.95Improved
add DDVM disparity-to-depth mapping (ablation)FoundationSSC (FE only) · SemanticKITTI valIoU: 46.61 -> 47.93Improved
add both GCA and DDVM (ablation)FoundationSSC (FE only) · SemanticKITTI valmIoU: 18.59 -> 19.56Improved
add Axis-Aware Fusion (ablation)FoundationSSC (FE+GCA+DDVM) · SemanticKITTI valmIoU: 19.56 -> 20.36Improved
use DDVM instead of CGFormer depth refinement (ablation)FoundationSSC · SemanticKITTI valmIoU: 19.83 -> 20.36Improved
use analytical resampling of the cost volume instead of learned DDVM (ablation)FoundationSSC · SemanticKITTI valmIoU: 20.36 -> 19.59Hurt
use vanilla 3D channel attention fusion instead of AAF (ablation)FoundationSSC · SemanticKITTI valmIoU: 20.36 -> 20.08Hurt
3D channel attention fusion of Flss and Fvt versus Fvt alone (ablation)FoundationSSC · SemanticKITTI valmIoU: 19.56 -> 20.08Improved
replace EfficientNet-B7 with DINOv2-L backbone (ablation)FoundationSSC · SemanticKITTI valmIoU: 15.20 -> 17.79Improved
use depth-specialised DepthAnythingV2-L instead of DINOv2-L (ablation)FoundationSSC · SemanticKITTI valIoU: IoU 45.88 -> 46.19, mIoU 17.79 -> 17.01Mixed
use small VFM (DINOv2-S) instead of EfficientNet-B7 (ablation)FoundationSSC · SemanticKITTI valmIoU: 15.20 -> 15.52Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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