AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

HiFi-BRep: High-Fidelity Latent Representation for Robust B-Rep Generation

Junhao Hou, Chenqi Luo, Pufan Wang, Jiaying Lu, Yusheng Liu, Feiwei Qin, Meie Fang, Kun Zhou

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 0 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 one-stage joint decoding of geometry and topology (ablation)HiFi-BRep · DeepCAD reconstructionValid (%): 69.3 -> 95.2Improved
use one-stage joint decoding of geometry and topology (ablation)HiFi-BRep · DeepCAD reconstructionAdj Acc (%): 73.2 -> 97.5Improved
add row-wise two-peak adjacency objective instead of independent BCE (ablation)HiFi-BRep · DeepCAD reconstructionValid (%): 87.2 -> 95.2Improved
add row-wise two-peak adjacency objective (ablation)HiFi-BRep · DeepCAD reconstructionAdj Acc (%): 90.4 -> 97.5Improved
add encoder Topo-Mask (ablation)HiFi-BRep · DeepCAD reconstructionValid (%): 89.5 -> 95.2Improved
add encoder Topo-Mask (ablation)HiFi-BRep · DeepCAD reconstructionAdj Acc (%): 92.7 -> 97.5Improved
add encoder Topo-Mask (ablation)HiFi-BRep · DeepCAD reconstructionFace Acc (%): 99.3 -> 100.0Improved
add canonicalization (lexicographic sorting of primitives) (ablation)HiFi-BRep · DeepCAD reconstructionValid (%)Improved
use HiFi-BRep single-stage design instead of DTGBrepGenHiFi-BRep vs DTGBrepGen · DeepCAD unconditional generationValid (%): 43.20 -> 72.20Improved
use HiFi-BRep instead of DTGBrepGenHiFi-BRep vs DTGBrepGen · ABC unconditional generationValid (%): 24.88 -> 32.66Improved
use HiFi-BRep instead of DTGBrepGenHiFi-BRep vs DTGBrepGen · ABC unconditional generationCOV: 70.63 -> 57.93Hurt
use HiFi-BRep instead of DTGBrepGenHiFi-BRep vs DTGBrepGen · DeepCAD unconditional generationCompilability-Valid gap: 49.28 -> 18.18Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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