CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Pose

Li Jin; Yuchen Yang; Weikai Chen; Yujie Wang; Dehao Hao; Tanghui Jia; Yingda Yin; Zeyu Hu

cs.CVMar 7, 2026

CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Pose

Authors: Li Jin, Yuchen Yang, Weikai Chen, Yujie Wang, Dehao Hao, Tanghui Jia, Yingda Yin, Zeyu Hu,

Organizations: SDU · LIGHTSPEED · UNC Chapel Hill · HKUST ·

Abstract

3D learning systems implicitly assume that objects occupy a coherent reference frame. Nonetheless, in practice, every asset arrives with an arbitrary global rotation, and models are left to resolve directional ambiguity on their own. This persistent misalignment suppresses pose-consistent generation, and blocks the emergence of stable directional semantics. To address this issue, we construct \methodName{}, a massive canonical 3D dataset of 320K objects over 1,156 categories -- an order-of-magnitude increase over prior work. At this scale, directional semantics become statistically learnable: Canoverse improves 3D generation stability, enables precise cross-modal 3D shape retrieval, and unlocks zero-shot point-cloud orientation estimation even for out-of-distribution data. This is achieved by a new canonicalization framework that reduces alignment from minutes to seconds per object via compact hypothesis generation and lightweight human discrimination, transforming canonicalization from manual curation into a high-throughput data generation pipeline. The Canoverse dataset will be publicly released upon acceptance. Project page: https://github.com/123321456-gif/Canoverse

Figures & tables

Figure 1: We present CanoVerse, a large-scale canonical dataset standardizing object orientation, size, and position with intra- and inter-category alignment. It contains 1,156 categories and 320k objects, making it the largest canonical dataset to date, an order of magnitude larger than existing ones.

Figure 2: Scale and category coverage of different canonical datasets. Our dataset boasts the largest number of categories and objects among existing canonical datasets—far surpassing each individual one and even the total of all aforementioned datasets.

Figure 3: 3D canonicalization pipeline. Left: prior manual alignment ( $\sim$ 101.4 s/object) yields small-scale datasets. Right: our candidate generation ( $\sim$ 3 s) plus one-click selection ( $\sim$ 2.7 s) gives $\sim$ 37.5 $\times$ faster annotation and enables a 320K canonical dataset.

Figure 4: For symmetric categories, we annotate the symmetry axis and angle (left). Due to diverse object shapes, unified annotation is impractical. We thus design separate standards based on object characteristics and generate candidate poses in the vertical (middle) and horizontal (right) directions.

Figure 5: Annotation statistics. 750K annotated; 51 $\%$ discarded for quality, 6 $\%$ for pose errors, 43 $\%$ retained (middle). Main discard types including thin-shell meshes, meaningless structures (left). Selection distribution over the 5 candidates (right).

Figure 6: Category coverage (left) and long-tailed distribution with more shapes per category than COD (right). Vertical axis: linear below 0.1, exponential above.

Figure 7: Qualitative comparison of the performance between our model and Orient Anything [ 30 ] on the OmniObject3D [ 34 ] dataset shows that the model trained on our dataset has better generalization ability.

Method	Acc@ $10^{\circ}\uparrow$	Acc@ $30^{\circ}\uparrow$	Abs $\downarrow$
PCA	22.98	34.83	91.49
CleanPose(CanoVerse) [ 15 ]	35.02	57.36	60.72
AGPose(CanoVerse) [ 16 ]	23.80	48.88	70.39
SecondPose(CanoVerse) [ 4 ]	49.15	58.39	60.11
VI-Net(Objaverse-OA) [ 14 ]	21.77	25.86	97.69
VI-Net(CanoVerse) [ 14 ]	55.31	64.14	51.47

Table 1: In-distribution comparisons for orientation estimation. Best results in bold .

Figure 8: Scalability Analysis on the in-distribution dataset. Left: COD vs. Ours at 32K samples. Right: Ours performance versus dataset size (32K → 310K). For metrics: higher Acc@10° and Acc@30° are better; lower Abs error is better.

Method	Acc@ $10^{\circ}\uparrow$	Acc@ $30^{\circ}\uparrow$	Abs $\downarrow$
GenPose++ [ 40 ]	4.33	6.95	105.17
Orient Anything [ 30 ]	4.77	7.32	103.11
VI-Net(Nocs) [ 14 ]	3.92	6.64	108.51
VI-Net(Objaverse-OA) [ 14 ]	6.56	9.60	105.90
VI-Net(CanoVerse) [ 14 ]	20.18	24.83	94.60

Table 2: Out-of-distribution orientation estimation results on the real-world scanned dataset OmniObject3D [ 34 ] .

Figure 9: Qualitative analysis of 3D object generation. Fine-tuning with canonical representation outperforms fine-tuning without it in semantics, aspect ratio, and structure.

		Toys4K				GSO
Method	canon.	CD $\downarrow$	LPIPS $\downarrow$	CLIP $\uparrow$	IQR( ∘ ) $\downarrow$	CD $\downarrow$	LPIPS $\downarrow$	CLIP $\uparrow$	IQR( ∘ ) $\downarrow$
Trellis [ 37 ]	w/o	0.227	0.436	89.7	48.5	0.272	0.468	88.0	74.0
Trellis [ 37 ]	w	0.095	0.254	93.9	7.7	0.072	0.244	92.5	8.1
Hun. 2.1 [ 28 ]	w/o	0.258	0.413	90.8	75.59	0.244	0.471	88.1	74.02
Hun. 2.1 [ 28 ]	w	0.085	0.260	93.7	8.1	0.090	0.288	90.6	18.6

Table 3: 3D Object Generation comparison results. Lower IQR(degree) indicates better pose stability. All variants are fine-tuned for the same total training time.

			Canoverse		OmniObject3D
Method	Canon.	Modality	Re.@10 $\uparrow$	Re.@30 $\uparrow$	Re.@10 $\uparrow$	Re.@30 $\uparrow$
ULIP [ 38 ]	w/o	Text	21.33	35.17	8.19	15.98
Uni3d [ 44 ]	w/o	Text	51.29	62.18	34.21	48.38
ULIP [ 38 ]	w	Text	25.05	39.43	9.95	19.89
Uni3d [ 44 ]	w	Text	53.88	64.31	35.88	49.02
ULIP [ 38 ]	w/o	Image	19.03	32.39	8.46	16.55

Table 4: Quantitative Comparison of Retrieval Performance. Higher Recall@10 and Recall@30 scores indicate better retrieval performance.

Method	Speed (s/object)			Precision (°)
Method	Low	Medium	High	Low	Medium	High
Blender (Manual)	125.3	101.4	94.5	8.2	4.5	3.7
COD [ 10 ]	4.6	3.4	3.0	9.4	8.5	8.1
Ours	4.0	2.7	2.6	6.7	6.3	5.9

Table 5: Annotation Speed and Precision Comparison. Smaller is better for both speed (s/object) and precision (°). Best results are in Bold , and second best is underlined .

Method	Aeroplane		Car		Bowl		Camera		Bottle		Can		Mug		Avg
Method	IC	GEC	IC	GEC	IC	GEC	IC	GEC	IC	GEC	IC	GEC	IC	GEC	IC	GEC
CaCa [ 26 ]	0.785	0.869	1.985	1.881	1.569	1.895	1.294	1.451	2.632	3.080	1.797	2.095	0.661	0.655	1.532	1.704
ConDor [ 23 ]	0.823	1.391	0.605	0.782	0.898	1.202	1.035	1.529	1.108	1.261	1.048	1.753	0.126	0.189	0.806	1.158
ShapeMat. [ 6 ]	0.659	2.337	2.409	3.596	0.368	0.452	0.377	1.491	1.279	3.791	1.369	2.211	0.399	0.629	0.980	2.072
COD [ 10 ]	0.051	0.058	0.103	0.118	0.011	0.012	1.116	1.177	0.031	0.034	0.030	0.037	0.018	0.019	0.194	0.208
Ours	0.129	0.176	0.007	0.012	0.018	0.032	0.033	0.584	0.009	0.012	0.005	0.017	0.022	0.026	0.032	0.123

Table 6: Comparison of 3D object canonicalization on the DREDS [ 5 ] dataset.

3D Shape Retrieval

See all 8 papers

CANIS: Generation-Assisted 3D Canonicalization via an Image-Semantic Bridge
Aug 7, 2026Kendong Liu, Yuxin Yao, Junhui Hou3D Scene Understanding
The authors are with the Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China
Pose-Aware Diffusion for 3D Generation
May 1, 2026Zihan Zhou, Luxi Chen, Jingzhi Zhou +43D Asset Generation 3D Scene Generation
Gaoling School of AI, Renmin University of China · VCIP, School of Computer Science, Nankai University · THU-Bosch MLCenter, Tsinghua University +1
Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction
Sep 20, 2026Yang-Tian Sun, Tianjia Liu, Zehuan Huang +73D Reconstruction 3D Scene Layout Generation
The University of Hong Kong · VAST

Aug 7, 2026J/K move · Enter open · S save

CANIS: Generation-Assisted 3D Canonicalization via an Image-Semantic Bridge

Kendong Liu, Yuxin Yao, Junhui Hou

The authors are with the Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China

3D Scene Understanding

Open paper AskPDF arXiv

Canonicalizing 3D object orientation is fundamental to 3D understanding and analysis. Existing approaches often rely on geometric cues, although 3D canonicalization ultimately requires a semantically meaningful orientation. To address this gap, we propose CANIS, a category-agnostic, generation-assisted framework that introduces the semantic orientation prior of a frozen image-to-3D generative model into 3D canonicalization, without canonicalization-specific training or category-specific templates. Specifically, CANIS first renders the input object from candidate viewpoints, selects an informative view, and generates a proxy in a canonical orientation. During generation, a sparse structural latent encoded from the input guides the proxy to preserve the geometry of an object. CANIS then uses the selected image as a semantic bridge between the input and the proxy. Image patches identify semantic regions on the proxy, and depth back-projection locates the corresponding regions on the input. The resulting semantic anchors constrain geometric matching, from which we estimate the rigid transformation that canonicalizes the input. Experiments on synthetic benchmarks validate CANIS and its key components, while qualitative results on partial observations and OmniObject3D suggest its applicability to incomplete and real-world scans. CANIS also improves downstream 3D classification, part segmentation, and dense correspondence under arbitrary rotations. Project page: https://kenkenzaii.github.io/Canis.

Abstract

3D Shape Retrieval

Explore similar work

CANIS: Generation-Assisted 3D Canonicalization via an Image-Semantic Bridge

Pose-Aware Diffusion for 3D Generation

Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction