AI Paper Atlas

Research map / 3D vision / 3D generation

Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion

Bohan Li, Jiajun Deng, Wenyao Zhang, Zhujin Liang, Dalong Du, Xin Jin, Wenjun Zeng

ECCV 2024 · 3D vision › 3D generation · approach: Semantic scene completion · 25 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
use temporal feature volume instead of cost volume (ablation)HTCL-S · SemanticKITTI valmIoU: 16.02 -> 17.13Improved
add scale-aware isolation to cosine affinity (ablation)HTCL-S CPA · SemanticKITTI valmIoU: 15.18 -> 17.13Improved
add multi-group context generation (ablation)HTCL-S CPA · SemanticKITTI valmIoU: 15.26 -> 17.13Improved
add affinity weights to dynamic refinement (ablation)HTCL-S ADR · SemanticKITTI valmIoU: 14.65 -> 17.13Improved
use deformable convolutions instead of normal convolutions (ablation)HTCL-S ADR · SemanticKITTI valmIoU: 15.14 -> 17.13Improved
add learnable coefficient in weighted voxel attention (ablation)HTCL-S WVA · SemanticKITTI valmIoU: 15.85 -> 17.13Improved
use voxel cross-attention instead of concatenation (ablation)HTCL-S WVA · SemanticKITTI valmIoU: 15.98 -> 17.13Improved
use more than 3 previous temporal frames (ablation)HTCL-S · SemanticKITTI valmIoUNo clear effect
use 5 context groups instead of 3 (ablation)HTCL-S CPA · SemanticKITTI valmIoU: 17.13 -> 17.21No clear effect
use 5 deformable levels instead of 3 (ablation)HTCL-S ADR · SemanticKITTI valmIoU: 17.13 -> 17.18No clear effect
use 3 deformable levels instead of 1 (ablation)HTCL-S ADR · SemanticKITTI valmIoU: 16.51 -> 17.13Improved
give stacked-temporal-stereo variants of single-frame baselines the same temporal inputsMonoScene, TPVFormer, OccFormer · SemanticKITTI valmIoU: 12.96, 13.21, 13.57 vs HTCL-S 17.13No clear effect

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