Scaling Versatile 3D Assets Editing with a Million-Scale Dataset

Badi Li; Tianxin Huang; Yu Zhou; Wei-Shi Zheng; Yi Ma; Shenghua Gao

cs.CVSep 28, 2026

Scaling Versatile 3D Assets Editing with a Million-Scale Dataset

Authors: Badi Li, Tianxin Huang, Yu Zhou, Wei-Shi Zheng, Yi Ma, Shenghua Gao

Organizations: The University of Hong Kong · Shenzhen Loop Area Institute · Sun Yat-Sen University · Shanghai Innovation Institute

Abstract

Although recent 3D generative models produce increasingly realistic assets, controllable 3D asset editing remains challenging. Existing methods are limited by scarce training data, insufficient source-aware modeling, and a lack of practical evaluation protocols. To address these limitations, we present Alchemy3D, a unified framework for training and evaluating versatile 3D asset editors that covers data construction, model architecture, and benchmark evaluation. Specifically, we curate Alchemy3D-1M, a large-scale 3D editing dataset containing 1.25M assets and 1.38M editing pairs across seven editing types. On this data, we train a family of generative flow models for general-purpose 3D asset editing. The model family supports image- and text-conditioned editing, few-step inference, and transfer to multi-view 3D part segmentation. We further introduce GEdit3D-Bench, a large-scale, open-world benchmark with a multi-dimensional evaluation protocol. Across existing and newly introduced benchmarks, our method outperforms prior methods on most metrics of editing fidelity, source preservation, and visual quality.

Figures & tables

Figure 1: Given a 3D asset and an editing instruction, our method edits the asset accordingly while preserving unrelated regions.

Dataset	Scale	PBR	Editing Types
			Add	Remove	Replace	Appearance	Animation	Segmentation
Steer3D	100K	✗	✓	✓	✗	✓	✗	✗
Nano3D-100K (ICLR’26)	100K	✗	✓	✓	✓	✗	✗	✗
3DEditVerse (ICML’26)	116K	✗	✓	✓	✓	✗	✗	✗
PxForm (SIGGRAPH Asia’26)	102K	✗	✓	✓	✓	✓	✗	✗
Alchemy3D-1M	1.38M	✓	✓	✓	✓	✓	✓	✓

Table 1: Comparison of existing 3D asset editing datasets. Our Alchemy3D-1M incorporates more diverse editing types and is more than 10

\times

larger in scale than existing related datasets.

Figure 2: Statistics of Alchemy3D-1M dataset. Alchemy3D-1M includes 1.25M unique assets and 1.38 M editing pairs, across 7 different editing types.

Figure 3: Illustration of Alchemy3D model. Following Trellis.2, we design a three-stage editing pipeline that sequentially edits sparse structure (voxel occupancy), geometry (fine-grained surface), and material (PBR attributes). Each stage comprises hybrid attention blocks that denoise noisy target tokens by attending to source tokens from the source asset alongside condition tokens from image/text instructions. For clarity, we display decoded outputs from denoised tokens at each stage.

Figure 4: Qualitative comparison between Alchemy3D and baselines. We show only addition, removal, and replacement, the editing types supported by all baselines.

Figure 5: (a) Examples from Alchemy3D-Instruct. (b) Segmentation results from Alchemy3D-Segment, where the segmentation criterion (e.g., semantic or instance) is controlled by the image instruction. (c) Comparison between Alchemy3D and Alchemy3D-Flux.

	View Qual.		Ref. Alignment			MLLM				Human	Time
Method	Aes. $\uparrow$	MUSIQ $\uparrow$	$A_{I}^{\mathrm{CLIP}}$ $\uparrow$	$A_{T}^{\mathrm{CLIP}}$ $\uparrow$	$A_{I}^{\mathrm{DINO}}$ $\uparrow$	SR $\uparrow$	VQ $\uparrow$	IF $\uparrow$	IP $\uparrow$	Pref.	(s) $\downarrow$
Nano3D	4.40	72.87	81.59	65.10	69.15	51.14%	70.16	53.84	72.09	5.1%	8.629
3DEditFormer	4.34	70.87	81.83	63.19	68.07	58.90%	66.31	59.79	63.39	5.3%	3.262
PartFlow	4.31	70.96	81.25	62.24	67.78	55.50%	65.27	56.20	66.60	6.5%	7.184
Alchemy3D-Turbo	4.58	72.94	82.36	68.31	72.88	88.18%	69.91	70.71	73.22	–	1.231
Alchemy3D	4.43	72.36	84.91	67.47	73.18	89.55%	72.74	71.38	76.19	70.7%	5.202

Table 2: Quantitative results on GEdit3D-Bench for addition, removal, and replacement. Per-type results are reported in Table 9 . Human preference scores do not sum to 100% because participants could also select a “tie” option when neither result was clearly better. Sampling time is measured on a single NVIDIA H200 GPU and averaged over 10 examples.

	Add / Remove / Replace				Action				Style
Method	Aes.	$A_{I}$	$A_{T}$	SR	Aes.	$A_{I}$	$A_{T}$	SR	Aes.	$A_{I}$	$A_{T}$	SR
Nano3D	4.60	82.31	49.43	40.00%	–	–	–	–	–	–	–	–
3DEditFormer	4.55	81.78	49.24	70.97%	4.06	75.80	44.45	20.00%	–	–	–	–
PartFlow	4.51	81.59	49.32	67.86%	–	–	–	–	4.58	78.10	50.68	40.00%
Alchemy3D-Turbo	4.64	82.67	52.56	90.00%	4.33	79.96	51.46	90.00%	4.61	81.15	52.51	100.00%
Alchemy3D	4.60	83.77	52.10	83.87%	4.29	80.84	51.15	80.00%	4.64	82.40	54.41	90.00%

Table 3: Quantitative results on Eval3DEdit. Since Eval3DEdit originally only evaluates CLIP similarities, we additionally report aesthetic score for view quality and SR for MLLM rating.

Explore similar work

Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
Aug 3, 2026Junliang Ye, Kenkun Liu, Guocun Wang +13High-Fidelity 3D Generation 3D Generation
Tencent Hunyuan
Feedforward 3D Editing Learns from Semantic-Part Transformation
May 26, 2026Jiawei Weng, Saining Zhang, Zhenxin Diao +43D Editing 3D Generation
Tsinghua University, China
EditFlow3D: Automated Local Editing of 3D Assets with Trajectory Preservation
Aug 4, 2026Rui Nie, Chuang Wang, Haitao Zhou +43D Editing 3D Assets
Beihang University · Bambu Lab · Shanghai Jiao Tong University

Aug 3, 2026, cs.CVJ/K move · Enter open · S save

Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing

Junliang Ye, Kenkun Liu, Guocun Wang, Yang Li+12

Tencent Hunyuan

High-Fidelity 3D Generation 3D Generation Multimodal Model

Open paper AskPDF arXiv

Recent advances in image generation have demonstrated the potential of unified multimodal models that integrate understanding, generation, and editing. However, unified 3D modeling remains constrained by scarce multimodal data, particularly the lack of large-scale and geometrically consistent editing data. To address this limitation, we propose Hunyuan3D-Buffalo 1.0, a unified framework supporting 3D understanding, text-to-3D generation, instruction-guided 3D editing, and text-grounded part generation within a single architecture. To enable scalable training, we construct an 87M-scale 3D multimodal corpus, comprising 25M understanding samples, 50M text-to-3D pairs, and 12M editing pairs generated using Nano3D-v2. Architecturally, the framework combines Hunyuan3D-VLM for semantic, structural, and spatial understanding with Hunyuan3D DiT for high-fidelity 3D synthesis. The VLM provides multimodal semantic conditions for generation, while editing and part generation additionally condition the diffusion process on the source object representation to preserve its overall structure and unedited regions. Extensive experiments show that Hunyuan3D-Buffalo 1.0 achieves state-of-the-art or leading performance on text-to-3D generation and 3D editing benchmarks, while exhibiting strong understanding and part-generation capabilities. Our analysis further shows that both generation and understanding improve editing, demonstrating the effectiveness of unified 3D multimodal training. Project Page: https://tencent-hunyuan.github.io/Hunyuan3D-Buffalo1.0/

Abstract

Explore similar work

Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing

Feedforward 3D Editing Learns from Semantic-Part Transformation

EditFlow3D: Automated Local Editing of 3D Assets with Trajectory Preservation