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

• URL: http://arxiv.org/abs/2608.16485v2
• Date: Tue, 18 Aug 2026 02:23:14 GMT
• Title: HiFi-BRep: High-Fidelity Latent Representation for Robust B-Rep Generation
• Abstract summary: Boundary representation (B-Rep) generation is a fundamental task in computer-aided design.<n>We propose HiFi-BRep, a novel framework that addresses these limitations through two synergistic contributions.<n>We show that HiFi-BRep significantly outperforms state-of-the-art methods in both structural validity and geometric fidelity.
• Score: 16.881723435082524
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Towards Valid B-Rep Generation: Training-Free Wireframe Anomaly Detection and Repair [11.44214616902057]
  Multistage representation (triggered computation generation) generates CAD models.<n>Risks such as self-intersections propagate invalid final validity of BReps.<n>We propose a framework to intervene at the Wireframe Detection stage to improve downstream BRep validity.
  arXiv  Detail & Related papers  (2026-08-05T15:24:58Z)
• C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders [56.67585330425431]
  Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features.<n>These issues stem from inconsistent latent assignment across samples.<n>We introduce C$2$R, which penalizes the co-activation of directionally similar latents.
  arXiv  Detail & Related papers  (2026-06-29T17:45:31Z)
• FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolution [3.479971042921974]
  We propose FreqOrtho-SR, which routes inputs to specialized experts via a non-parametric FFT-based degradation-feature extractor.<n>$textbfOrtho$gonal Gradient Projection (OGP) reframes the dual-objective optimization as a subspace-constrained problem.<n>Experiments show that FreqOrtho-SR achieves competitive overall performance and a strong fidelity-perception trade-off.
  arXiv  Detail & Related papers  (2026-06-27T05:51:23Z)
• PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution [51.96078493242164]
  PRISM is a single-step diffusion-based Text-SR framework.<n> PRISM achieves state-of-the-art performance with millisecond-level inference.
  arXiv  Detail & Related papers  (2026-05-13T05:31:06Z)
• Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering [57.38215918201251]
  We propose HERL, a Hyperbolic Enhanced Representation Learning framework for Incomplete Multi-View Clustering.<n> operating within the Poincaré ball, HERL constructs a structure-aware latent space to enhance representation learning.<n>We show that HERL consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-04-18T10:50:46Z)
• Joint Geometric and Trajectory Consistency Learning for One-Step Real-World Super-Resolution [14.52346301984322]
  Diffusion-based Real-World Image Super-Resolution (Real-ISR) achieves impressive perceptual quality but suffers from high computational costs due to iterative sampling.<n>We propose GTASR (Geometric Trajectory Alignment Super-Resolution), a simple yet effective consistency training paradigm for Real-ISR.
  arXiv  Detail & Related papers  (2026-02-27T18:13:31Z)
• AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometry [13.357641924794402]
  The boundary representation (B-Rep) is the standard data structure used in Computer-Aided Design (CAD) for defining solid models.<n>This paper presents AutoBrep, a novel Transformer model that autoregressively generates B-Reps with high quality and validity.
  arXiv  Detail & Related papers  (2025-12-02T18:46:25Z)
• BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch [61.20046418942948]
  Boundary representation (B-rep) is the de facto standard for CAD model representation in modern industrial design.<n>We present BrepGPT, a single-stage autoregressive framework for B-rep generation.
  arXiv  Detail & Related papers  (2025-11-27T07:16:53Z)
• Few-shot Class-incremental Fault Diagnosis by Preserving Class-Agnostic Knowledge with Dual-Granularity Representations [16.182587421358235]
  Few-Shot Class-Incremental Fault Diagnosis (FSC-FD) is critical for real-world industrial systems.<n>This paper proposes a novel framework built upon Dual-Granularity Representations, termed the Dual-Granularity Guidance Network (DGGN)<n>Our proposed DGGN achieves superior diagnostic performance and stability compared to state-of-the-art FSC-FD approaches.
  arXiv  Detail & Related papers  (2025-08-16T03:14:07Z)
• HoLa: B-Rep Generation using a Holistic Latent Representation [51.07878285790399]
  We introduce a novel representation for learning and generating Computer-Aided Design (CAD) models in the form of $textitboundary representations$ (B-Reps)<n>Our representation unifies the continuous geometric properties of B-Rep primitives in different orders.<n>Our method significantly reduces ambiguities, redundancies, and incoherences among the generated B-Rep primitives.
  arXiv  Detail & Related papers  (2025-04-19T10:34:24Z)
• Towards Robust and Realistic Human Pose Estimation via WiFi Signals [85.60557095666934]
  WiFi-based human pose estimation is a challenging task that bridges discrete and subtle WiFi signals to human skeletons.<n>This paper revisits this problem and reveals two critical yet overlooked issues: 1) cross-domain gap, i.e., due to significant variations between source-target domain pose distributions; and 2) structural fidelity gap, i.e., predicted skeletal poses manifest distorted topology.<n>This paper fills these gaps by reformulating the task into a novel two-phase framework dubbed DT-Pose: Domain-consistent representation learning and Topology-constrained Pose decoding.
  arXiv  Detail & Related papers  (2025-01-16T09:38:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.