mlsanityData to 14 Oct 2026

MagicGarment: Benchmarking Single-Image Standalone 3D Garment Reconstruction

arXiv 2610.19623 ↗First posted 14 Oct 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Single-image 3D reconstruction has advanced rapidly, yet standalone garments remain challenging due to thin-shell geometry, open boundaries, and layered structures. Existing datasets and evaluation protocols provide limited support for systematic evaluation in this setting. We introduce MagicGarment, a benchmark for single-image standalone 3D garment reconstruction with 1,518 professionally constructed assets across 17 composite garment types, aligned multimodal annotations, and a unified evaluation protocol. We further establish a garment-aware reference baseline by adapting a pretrained image-to-3D backbone at two levels: Grounded Semantic Refinement (GSR) provides garment-focused visual conditioning, while Flow-Time-Route LoRA (FTR-LoRA) adapts the frozen 3D generative backbone using flow-timestep, token-routing, and expert-load information. Experiments demonstrate MagicGarment's benchmark utility and the effectiveness of garment-aware adaptation. Project page: https://1019538157.github.io/MagicGarment/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 27 references that are in the map. First posted on arXiv 14 Oct 2026.

Builds on

23 of 27 references.

References · 23

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  3. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  4. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  5. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 689
  6. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  7. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  8. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 267
  9. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 245
  10. 2023A Rank Stabilization Scaling Factor for Fine-Tuning with LoRAcited by 243
  11. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 237
  12. 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 215
11 more
  1. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 202
  2. 2025Native and Compact Structured Latents for 3D Generationcited by 175
  3. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 165
  4. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Imagecited by 135
  5. 2020BCNet: Learning Body and Cloth Shape from A Single Imagecited by 120
  6. 2019CLOTH3D: Clothed 3D Humanscited by 116
  7. 2020Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Imagescited by 103
  8. 20244D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotationscited by 54
  9. 2022DrapeNet: Garment Generation and Self-Supervised Drapingcited by 41
  10. 2024ZIM: Zero-Shot Image Matting for Anythingcited by 16
  11. 2024GarVerseLOD: High-Fidelity 3D Garment Reconstruction from a Single In-the-Wild Image using a Dataset with Levels of Detailscited by 16

Built on by

Not cited yet.