HY3D-Bench: Generation of 3D Assets

• URL: http://arxiv.org/abs/2602.03907v1
• Date: Tue, 03 Feb 2026 14:13:09 GMT
• Title: HY3D-Bench: Generation of 3D Assets
• Abstract summary: HY3D-Bench is an open-source ecosystem designed to establish a unified, high-quality foundation for 3D generation.<n>We curate a library of 250k high-fidelity 3D objects distilled from large-scale repositories, employing a rigorous pipeline to deliver training-ready artifacts.<n>We bridge real-world distribution gaps via a scalable AIGC synthesis pipeline, contributing 125k synthetic assets to enhance diversity in long-tail categories.
• Score: 35.60878644543142
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: While recent advances in neural representations and generative models have revolutionized 3D content creation, the field remains constrained by significant data processing bottlenecks. To address this, we introduce HY3D-Bench, an open-source ecosystem designed to establish a unified, high-quality foundation for 3D generation. Our contributions are threefold: (1) We curate a library of 250k high-fidelity 3D objects distilled from large-scale repositories, employing a rigorous pipeline to deliver training-ready artifacts, including watertight meshes and multi-view renderings; (2) We introduce structured part-level decomposition, providing the granularity essential for fine-grained perception and controllable editing; and (3) We bridge real-world distribution gaps via a scalable AIGC synthesis pipeline, contributing 125k synthetic assets to enhance diversity in long-tail categories. Validated empirically through the training of Hunyuan3D-2.1-Small, HY3D-Bench democratizes access to robust data resources, aiming to catalyze innovation across 3D perception, robotics, and digital content creation.

Related papers

• PLSR: Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion [44.63283515238481]
  High-resolution 3D asset generation is vital in various 3D applications.<n>Existing state-of-the-art diffusion-based models remain constrained by fixed resolutions.<n>We introduce a 3D super-resolution framework built on existing 3D generative foundation models.
  arXiv  Detail & Related papers  (2026-09-06T07:21:36Z)
• DeepJEB++: Foundation Model-Driven Large-Scale 3D Engineering Dataset via 2D Latent Space Augmentation [4.353545088427288]
  DeepJEB++ is a foundation-model-driven data-augmentation framework.<n>It expands a small seed set of jet engine brackets into a large, simulation-labeled 3D dataset.<n>Starting from fewer than 400 seed designs, DeepJEB++ yields 15,360 simulation-labeled 3D brackets.
  arXiv  Detail & Related papers  (2026-06-11T07:30:56Z)
• Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models [66.3899679538548]
  Generative 3D models are deployed in gaming, robotics, and immersive creation.<n>Can we identify whether and which generative model created it?<n>This problem faces two core challenges: dispersed attribution signals and realistic deployment constraints.
  arXiv  Detail & Related papers  (2026-05-18T09:36:48Z)
• Particulate: Feed-Forward 3D Object Articulation [89.78788418174946]
  Particulate is a feed-forward approach that, given a single static 3D mesh of an everyday object, directly infers all attributes of the underlying articulated structure.<n>We train the network end-to-end on a diverse collection of articulated 3D assets from public datasets.<n>During inference, Particulate lifts the network's feed-forward prediction to the input mesh, yielding a fully articulated 3D model in seconds.
  arXiv  Detail & Related papers  (2025-12-12T18:59:51Z)
• Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets [90.99212668875971]
  Step1X-3D is an open framework addressing challenges such as data scarcity, algorithmic limitations, and ecosystem fragmentation.<n>We present a two-stage 3D-native architecture combining a hybrid VAE-DiT geometry generator with a diffusion-based texture synthesis module.<n> Benchmark results demonstrate state-of-the-art performance that exceeds existing open-source methods.
  arXiv  Detail & Related papers  (2025-05-12T16:56:30Z)
• TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models [69.0220314849478]
  TripoSG is a new streamlined shape diffusion paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images.<n>The resulting 3D shapes exhibit enhanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input images.<n>To foster progress and innovation in the field of 3D generation, we will make our model publicly available.
  arXiv  Detail & Related papers  (2025-02-10T16:07:54Z)
• Structured 3D Latents for Scalable and Versatile 3D Generation [28.672494137267837]
  We introduce a novel 3D generation method for versatile and high-quality 3D asset creation.<n>The cornerstone is a unified Structured LATent representation which allows decoding to different output formats.<n>This is achieved by integrating a sparsely-populated 3D grid with dense multiview visual features extracted from a powerful vision foundation model.
  arXiv  Detail & Related papers  (2024-12-02T13:58:38Z)
• 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion [86.25111098482537]
  We introduce 3DTopia-XL, a scalable native 3D generative model designed to overcome limitations of existing methods.<n>3DTopia-XL leverages a novel primitive-based 3D representation, PrimX, which encodes detailed shape, albedo, and material field into a compact tensorial format.<n>On top of the novel representation, we propose a generative framework based on Diffusion Transformer (DiT), which comprises 1) Primitive Patch Compression, 2) and Latent Primitive Diffusion.<n>We conduct extensive qualitative and quantitative experiments to demonstrate that 3DTopia-XL significantly outperforms existing methods in generating high-
  arXiv  Detail & Related papers  (2024-09-19T17:59:06Z)
• Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability [118.26563926533517]
  Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. We extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
  arXiv  Detail & Related papers  (2024-02-19T15:33:09Z)
• Pushing the Limits of 3D Shape Generation at Scale [65.24420181727615]
  We present a significant breakthrough in 3D shape generation by scaling it to unprecedented dimensions. We have developed a model with an astounding 3.6 billion trainable parameters, establishing it as the largest 3D shape generation model to date, named Argus-3D.
  arXiv  Detail & Related papers  (2023-06-20T13:01:19Z)

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.