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

Hugging Face Daily Papers Papers
b-rep boundary-representation topology-aware-encoder single-stage-decoder differentiable-constraints cad deep-learning

Summary

HiFi-BRep improves B-Rep generation by using a topology-aware encoder and single-stage decoder to jointly predict geometry and topology with differentiable constraints, enhancing structural validity and geometric fidelity.

Boundary representation (B-Rep) generation is a fundamental task in computer-aided design, yet the direct synthesis of high-fidelity and structurally valid B-Reps remains a major challenge. Existing deep generative methods suffer from two forms of brittleness: representation brittleness, caused by padding noise and feature contamination in the latent space, and generation brittleness, stemming from sequential error propagation and a train-inference mismatch due to non-differentiable validity enforcement. We propose HiFi-BRep, a novel framework that addresses these limitations through two synergistic contributions. First, a topology-aware encoder constructs a high-fidelity latent representation by eliminating padding via learnable queries and preventing feature contamination with topology-guided attention. Second, a single-stage decoder jointly predicts geometry and topology in parallel, embedding core manifold constraints as a differentiable learning objective. This design ensures mutual guidance between geometry and topology while avoiding cascaded errors. Extensive experiments show that HiFi-BRep significantly outperforms state-of-the-art methods in both structural validity and geometric fidelity, providing a robust solution for high-quality B-Rep synthesis. Code and models are publicly available at https://github.com/1nnoh/HiFi-BRep.
Original Article
View Cached Full Text

Cached at: 08/18/26, 07:51 AM

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

Source: https://huggingface.co/papers/2608.16485

Abstract

HiFi-BRep improves B-Rep synthesis by using a topology-aware encoder and a single-stage decoder that jointly predicts geometry and topology with differentiable validity constraints.

Boundary representation(B-Rep) generation is a fundamental task in computer-aided design, yet the direct synthesis of high-fidelity and structurally validB-Reps remains a major challenge. Existing deep generative methods suffer from two forms of brittleness: representation brittleness, caused by padding noise and feature contamination in the latent space, and generation brittleness, stemming from sequential error propagation and a train-inference mismatch due to non-differentiable validity enforcement. We propose HiFi-BRep, a novel framework that addresses these limitations through two synergistic contributions. First, atopology-aware encoderconstructs a high-fidelity latent representation by eliminating padding vialearnable queriesand preventing feature contamination withtopology-guided attention. Second, asingle-stage decoderjointly predicts geometry and topology in parallel, embedding coremanifold constraintsas adifferentiable learning objective. This design ensures mutual guidance between geometry and topology while avoiding cascaded errors. Extensive experiments show that HiFi-BRep significantly outperforms state-of-the-art methods in both structural validity and geometric fidelity, providing a robust solution for high-qualityB-Repsynthesis. Code and models are publicly available at https://github.com/1nnoh/HiFi-BRep.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2608\.16485

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### 1nnoh/HiFi-BRep Updatedabout 2 hours ago

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.16485 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.16485 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction

Hugging Face Daily Papers

Re2Pix is a hierarchical video prediction framework that improves future video generation by first predicting semantic representations using frozen vision foundation models, then conditioning a latent diffusion model on these predictions to generate photorealistic frames. The approach addresses train-test mismatches through nested dropout and mixed supervision strategies, achieving improved temporal semantic consistency and perceptual quality on autonomous driving benchmarks.

Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction

Hugging Face Daily Papers

Lite3R is a model-agnostic framework that improves the efficiency of transformer-based 3D reconstruction using sparse linear attention and FP8-aware quantization. It reduces latency and memory usage by up to 2.4x while maintaining geometric accuracy on backbones like VGGT and DA3-Large.