SYNTHIA: Novel Concept Design with Affordance Composition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909942192013312 |
|---|---|
| author | Ha, Hyeonjeong Jin, Xiaomeng Kim, Jeonghwan Liu, Jiateng Wang, Zhenhailong Nguyen, Khanh Duy Blume, Ansel Peng, Nanyun Chang, Kai-Wei Ji, Heng |
| author_facet | Ha, Hyeonjeong Jin, Xiaomeng Kim, Jeonghwan Liu, Jiateng Wang, Zhenhailong Nguyen, Khanh Duy Blume, Ansel Peng, Nanyun Chang, Kai-Wei Ji, Heng |
| contents | Text-to-image (T2I) models enable rapid concept design, making them widely used in AI-driven design. While recent studies focus on generating semantic and stylistic variations of given design concepts, functional coherence--the integration of multiple affordances into a single coherent concept--remains largely overlooked. In this paper, we introduce SYNTHIA, a framework for generating novel, functionally coherent designs based on desired affordances. Our approach leverages a hierarchical concept ontology that decomposes concepts into parts and affordances, serving as a crucial building block for functionally coherent design. We also develop a curriculum learning scheme based on our ontology that contrastively fine-tunes T2I models to progressively learn affordance composition while maintaining visual novelty. To elaborate, we (i) gradually increase affordance distance, guiding models from basic concept-affordance association to complex affordance compositions that integrate parts of distinct affordances into a single, coherent form, and (ii) enforce visual novelty by employing contrastive objectives to push learned representations away from existing concepts. Experimental results show that SYNTHIA outperforms state-of-the-art T2I models, demonstrating absolute gains of 25.1% and 14.7% for novelty and functional coherence in human evaluation, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17793 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SYNTHIA: Novel Concept Design with Affordance Composition Ha, Hyeonjeong Jin, Xiaomeng Kim, Jeonghwan Liu, Jiateng Wang, Zhenhailong Nguyen, Khanh Duy Blume, Ansel Peng, Nanyun Chang, Kai-Wei Ji, Heng Computer Vision and Pattern Recognition Artificial Intelligence Text-to-image (T2I) models enable rapid concept design, making them widely used in AI-driven design. While recent studies focus on generating semantic and stylistic variations of given design concepts, functional coherence--the integration of multiple affordances into a single coherent concept--remains largely overlooked. In this paper, we introduce SYNTHIA, a framework for generating novel, functionally coherent designs based on desired affordances. Our approach leverages a hierarchical concept ontology that decomposes concepts into parts and affordances, serving as a crucial building block for functionally coherent design. We also develop a curriculum learning scheme based on our ontology that contrastively fine-tunes T2I models to progressively learn affordance composition while maintaining visual novelty. To elaborate, we (i) gradually increase affordance distance, guiding models from basic concept-affordance association to complex affordance compositions that integrate parts of distinct affordances into a single, coherent form, and (ii) enforce visual novelty by employing contrastive objectives to push learned representations away from existing concepts. Experimental results show that SYNTHIA outperforms state-of-the-art T2I models, demonstrating absolute gains of 25.1% and 14.7% for novelty and functional coherence in human evaluation, respectively. |
| title | SYNTHIA: Novel Concept Design with Affordance Composition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.17793 |