AI Paper Atlas

Research map / Point clouds / Shape and surface completion

TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds

Elona Dupont, Kseniya Cherenkova, Dimitrios Mallis, Gleb A Gusev, Anis Kacem, Djamila Aouada

ECCV 2024 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 30 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 hierarchical loop-extrusion decoding (ablation)TransCAD · DeepCAD testAPCS: 0.687 -> 0.708 (w/o refining) / 0.732 (full)Improved
add loop refiner (ablation)TransCAD · DeepCAD testAPCS: 0.708 -> 0.732Improved
add loop refiner (also on extrusion APCS components) (ablation)TransCAD · DeepCAD testAPCS Ext. component: 0.755 -> 0.818Improved
TransCAD vs DeepCAD under Perlin noisepoint cloud noise · DeepCAD (Perlin noise)APCS: 0.550 -> 0.604Improved
increase Perlin noise magnitude by 50%TransCAD · DeepCAD (Perlin noise)APCS: 0.604 -> 0.532Hurt
finetune 2 epochs on noisy training dataTransCAD · DeepCAD (Perlin noise)APCS: 0.604 -> 0.724Improved
reduce input points from 4096 to 256TransCAD · DeepCAD testAPCS: 0.732 -> 0.673Hurt
use ground-truth loop/extrusion types at inference (ablation)TransCAD · DeepCAD testAPCS: 0.732 -> 0.790Improved
TransCAD vs retrieval baseline on chamfer distanceTransCAD · DeepCAD testChamfer distance (x10^3): 2.8 (retrieval) vs 4.5Hurt
TransCAD vs DeepCAD on Fusion360 APCSTransCAD · Fusion360 (cross-dataset)APCS: 0.360 -> 0.365No clear effect

Later papers that compared with this method

1 later accepted paper reports TransCAD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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