# Diff-SBSR: Learning Multimodal Feature-Enhanced Diffusion Models for Zero-Shot Sketch-Based 3D Shape Retrieval

arXiv: https://arxiv.org/abs/2604.19135 · HTML: https://mlsanity.com/paper/2604.19135/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 24 of its 60 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 24 of 24)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Learning SO(3) Equivariant Representations with Spherical CNNs](https://mlsanity.com/paper/1711.06721/) (2017)
- [Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models](https://mlsanity.com/paper/1704.01222/) (2017)
- [CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not](https://mlsanity.com/paper/2303.13440/) (2023)
- [SODA: Bottleneck Diffusion Models for Representation Learning](https://mlsanity.com/paper/2311.17901/) (2023)
- [Sketch-based 3D Shape Retrieval using Convolutional Neural Networks](https://mlsanity.com/paper/1504.03504/) (2015)
- [Medical diffusion on a budget: Textual Inversion for medical image generation](https://mlsanity.com/paper/2303.13430/) (2023)
- [What Can Human Sketches Do for Object Detection?](https://mlsanity.com/paper/2303.15149/) (2023)
- [CoGS: Controllable Generation and Search from Sketch and Style](https://mlsanity.com/paper/2203.09554/) (2022)
- [Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes](https://mlsanity.com/paper/2312.04043/) (2023)
- [SHREC'22 Track: Sketch-Based 3D Shape Retrieval in the Wild](https://mlsanity.com/paper/2207.04945/) (2022)
- [Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers](https://mlsanity.com/paper/2403.07214/) (2024)
- [Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape Retrieval](https://mlsanity.com/paper/1807.01806/) (2018)
- [What Sketch Explainability Really Means for Downstream Tasks](https://mlsanity.com/paper/2403.09480/) (2024)
- [SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models](https://mlsanity.com/paper/2503.14129/) (2025)
- [Elevating All Zero-Shot Sketch-Based Image Retrieval Through Multimodal Prompt Learning](https://mlsanity.com/paper/2407.04207/) (2024)

## Abstract (arXiv)

This paper presents the first exploration of text-to-image diffusion models for zero-shot sketch-based 3D shape retrieval (ZS-SBSR). Existing sketch-based 3D shape retrieval methods struggle in zero-shot settings due to the absence of category supervision and the extreme sparsity of sketch inputs. Our key insight is that large-scale pretrained diffusion models inherently exhibit open-vocabulary capability and strong shape bias, making them well suited for zero-shot visual retrieval. We leverage a frozen Stable Diffusion backbone to extract and aggregate discriminative representations from intermediate U-Net layers for both sketches and rendered 3D views. Diffusion models struggle with sketches due to their extreme abstraction and sparsity, compounded by a significant domain gap from natural images. To address this limitation without costly retraining, we introduce a multimodal feature-enhanced strategy that conditions the frozen diffusion backbone with complementary visual and textual cues from CLIP, explicitly enhancing the ability of semantic context capture and concentrating on sketch contours. Specifically, we inject global and local visual features derived from a pretrained CLIP visual encoder, and incorporate enriched textual guidance by combining learnable soft prompts with hard textual descriptions generated by BLIP. Furthermore, we employ the Circle-T loss to dynamically strengthen positive-pair attraction once negative samples are sufficiently separated, thereby adapting to sketch noise and enabling more effective sketch-3D alignment. Extensive experiments on two public benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches in ZS-SBSR.