BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining

• URL: http://arxiv.org/abs/2510.18244v1
• Date: Tue, 21 Oct 2025 03:08:27 GMT
• Title: BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining
• Authors: Ajinkya Khoche, Gergő László Nagy, Maciej Wozniak, Thomas Gustafsson, Patric Jensfelt,
• Abstract summary: Zero-shot 3D object classification is crucial for real-world applications like autonomous driving.<n>It is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans encountered in the real-world.<n>We introduce BlendCLIP, a multimodal pretraining framework that bridges this synthetic-to-real gap by strategically combining the strengths of both domains.
• Score: 2.400704807305413
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans encountered in the real-world. Current methods trained solely on synthetic data fail to generalize to outdoor scenes, while those trained only on real data lack the semantic diversity to recognize rare or unseen objects. We introduce BlendCLIP, a multimodal pretraining framework that bridges this synthetic-to-real gap by strategically combining the strengths of both domains. We first propose a pipeline to generate a large-scale dataset of object-level triplets -- consisting of a point cloud, image, and text description -- mined directly from real-world driving data and human annotated 3D boxes. Our core contribution is a curriculum-based data mixing strategy that first grounds the model in the semantically rich synthetic CAD data before progressively adapting it to the specific characteristics of real-world scans. Our experiments show that our approach is highly label-efficient: introducing as few as 1.5\% real-world samples per batch into training boosts zero-shot accuracy on the nuScenes benchmark by 27\%. Consequently, our final model achieves state-of-the-art performance on challenging outdoor datasets like nuScenes and TruckScenes, improving over the best prior method by 19.3\% on nuScenes, while maintaining strong generalization on diverse synthetic benchmarks. Our findings demonstrate that effective domain adaptation, not full-scale real-world annotation, is the key to unlocking robust open-vocabulary 3D perception. Our code and dataset will be released upon acceptance on https://github.com/kesu1/BlendCLIP.

Related papers

• UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass [83.7071371474926]
  UniSH is a unified, feed-forward framework for joint metric-scale 3D scene and human reconstruction.<n>Our framework bridges strong, disparate priors from scene reconstruction and HMR.<n>Our model achieves state-of-the-art performance on human-centric scene reconstruction.
  arXiv  Detail & Related papers  (2026-01-03T16:06:27Z)
• A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation [15.541453405140485]
  Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery.<n>We present a new framework that adapts an off-the-shelf diffusion model to a target domain using only imperfect pseudo-labels.<n>It generates high-fidelity, target-aligned images from semantic maps of any synthetic dataset, including low-effort sources created in hours rather than months.
  arXiv  Detail & Related papers  (2025-10-13T16:12:29Z)
• Private Training & Data Generation by Clustering Embeddings [74.00687214400021]
  Differential privacy (DP) provides a robust framework for protecting individual data.<n>We introduce a novel principled method for DP synthetic image embedding generation.<n> Empirically, a simple two-layer neural network trained on synthetically generated embeddings achieves state-of-the-art (SOTA) classification accuracy.
  arXiv  Detail & Related papers  (2025-06-20T00:17:14Z)
• BelHouse3D: A Benchmark Dataset for Assessing Occlusion Robustness in 3D Point Cloud Semantic Segmentation [2.446672595462589]
  We introduce the BelHouse3D dataset, a new synthetic point cloud dataset designed for 3D indoor scene semantic segmentation. This dataset is constructed using real-world references from 32 houses in Belgium, ensuring that the synthetic data closely aligns with real-world conditions.
  arXiv  Detail & Related papers  (2024-11-20T12:09:43Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• Robust Category-Level 3D Pose Estimation from Synthetic Data [17.247607850702558]
  We introduce SyntheticP3D, a new synthetic dataset for object pose estimation generated from CAD models. We propose a novel approach (CC3D) for training neural mesh models that perform pose estimation via inverse rendering.
  arXiv  Detail & Related papers  (2023-05-25T14:56:03Z)
• A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation [42.2398858786125]
  Deep learning in computer vision has achieved great success with the price of large-scale labeled training data. The uncontrollable data collection process produces non-IID training and test data, where undesired duplication may exist. To circumvent them, an alternative is to generate synthetic data via 3D rendering with domain randomization.
  arXiv  Detail & Related papers  (2023-03-16T09:03:52Z)
• Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Clouds [69.64240235315864]
  This paper introduces the synthetic-to-real domain generalization setting to this task. The domain gap between synthetic and real-world point cloud data mainly lies in the different layouts and point patterns. Experiments on the synthetic-to-real benchmark demonstrate that both CINMix and multi-prototypes can narrow the distribution gap.
  arXiv  Detail & Related papers  (2022-12-09T05:07:43Z)
• GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation [60.07812405063708]
  3D point cloud semantic segmentation is fundamental for autonomous driving. Most approaches in the literature neglect an important aspect, i.e., how to deal with domain shift when handling dynamic scenes. This paper advances the state of the art in this research field.
  arXiv  Detail & Related papers  (2022-07-20T09:06:07Z)
• Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding [62.17020485045456]
  It is commonly assumed in semi-supervised learning (SSL) that the unlabeled data are drawn from the same distribution as that of the labeled ones. We propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized.
  arXiv  Detail & Related papers  (2022-05-02T16:09:17Z)
• RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection [138.2892824662943]
  A promising solution is to make better use of the synthetic dataset, which consists of CAD object models, to boost the learning on real datasets. Recent work on 3D pre-training exhibits failure when transfer features learned on synthetic objects to other real-world applications. In this work, we put forward a new method called RandomRooms to accomplish this objective.
  arXiv  Detail & Related papers  (2021-08-17T17:56:12Z)

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.