cs.CVNov 2, 2026

GEAR: Generative Editing for Scene-Conditioned Outfit Retrieval for VR Travel

Authors: Gia-Huy Dinh, Thinh-Phuc Nguyen, Thanh-Hai Nguyen, Lam-Huy Nguyen-Ngoc, Hoang-Bach Nguyen-Phan, Nam-Quan Nguyen, Minh-Triet Tran, Trung-Nghia Le

Organizations: University of Science, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam

Abstract

In virtual environments, choosing appropriate outfits requires contextual harmony with surrounding scenes, yet bridging the visual gap between 3D ambient views and catalog garment assets remains challenging. This paper investigates scene-conditioned outfit retrieval for interactive 3D environments, where a user's egocentric view serves as the retrieval signal. We present GEAR (Generative Editing for Asset Retrieval), a framework that bridges the cross-domain gap by synthesizing intermediate visual queries rather than predicting direct compatibility. GEAR uses a vision-language model to describe suitable clothing from a captured scene, employs an instruction-guided diffusion model to render the concept onto a standardized reference character, and utilizes the cropped clothing region to retrieve existing 2D outfit assets via embedding similarity. An interactive Unity prototype demonstrates real-time scene capture, asset retrieval, and in-engine 3D avatar fitting. We benchmark GEAR against direct visual similarity, aesthetic scoring, and VLM-based reranking on a controlled dataset using automated Swiss-system pairwise judgments, where GEAR achieves competitive top-ranked performance (mean Elo@5 of 1012.75 and top-10 overlap of 0.180) alongside 0.539 pairwise agreement. Furthermore, a user study across 20 virtual travel scenes demonstrates that GEAR achieves the highest overall participant preference in both visual appeal (34.5%) and contextual suitability (34.5%).

Figures & tables

Explore similar work

CardsList
  1. Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off

    Mar 23, 2026Davide Lobba, Fulvio Sanguigni, Bin Ren +3Virtual Try-OnText-Guided Image Editing

  2. VersaVogue: Visual Expert Orchestration and Preference Alignment for Unified Fashion Synthesis

    Apr 8, 2026Jian Yu, Fei Shen, Cong Wang +4Image GenerationControllable Image Generation

  3. Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories

    Mar 14, 2026Junyao Hu, Zhongwei Cheng, Waikeung Wong +1Virtual Try-On