Saliency Guided Subdivision for Single-View Mesh Reconstruction

Li, Hai; Ye, Weicai; Zhang, Guofeng; Zhang, Sanyuan; Bao, Hujun

doi:10.1109/3dv50981.2020.00120

Cited by 5 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is used to score shape similarity between the two, therefore measuring the reconstruction quality of the method. This has been used to evaluate single-view [61], [62], [63] and multi-view [59] reconstruction approaches. For methods of interpolation, a separability score can be obtained to measure how disentangled the latent space is [64].…”

Section: Objective Similarity Metricsmentioning

confidence: 99%

“…Overlap [11], [12], [14] Alignment [11], [12] RMSD [13] [71], [113], [114], [56] 3D-text alignment (ShapeGlot) [124] Characteristic flood extent [133] Stability [134] Rootedness [134] Symmetry score [120] Mesh intersection ratio [62] CNR [25] Density [25] This article has been accepted for publication in IEEE Transactions on Pattern Analysis and Machine Intelligence. This is the author's version which has not been fully edited and content may change prior to final publication.…”

Section: Characteristicmentioning

confidence: 99%

“…This will be be dependent on the intended use case, and whether the characteristic can be objectively measured. For example, symmetry score [120] and mesh intersection ratio [62] are applied in quantifying the symmetry and self-intersection of 3D assets respectively. For road networks, or graphs in general, connected node ratio and density metrics [25] can be employed to examine the properties of the networks.…”

Section: Automatic Quality Metricsmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation metrics for intelligent generation of graphical game assets: a systematic survey-based framework

Fukaya,

Daylamani-Zad,

Agius

2024

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Generative systems for graphical assets have the potential to provide users with high quality assets at the push of a button. However, there are many forms of assets, and many approaches for producing them. Quantitative evaluation of these methods is necessary if practitioners wish to validate or compare their implementations. Furthermore, providing benchmarks for new methods to strive for or surpass. While most methods are validated using tried-and-tested metrics within their own domains, there is no unified method of finding the most appropriate. We present a framework based on a literature pool of close to 200 papers, that provides guidance in selecting metrics to evaluate the validity and quality of artefacts produced, and the operational capabilities of the method.

show abstract

Section: Objective Similarity Metricsmentioning

confidence: 99%

Section: Characteristicmentioning

confidence: 99%

Section: Automatic Quality Metricsmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation metrics for intelligent generation of graphical game assets: a systematic survey-based framework

Fukaya,

Daylamani-Zad,

Agius

2024

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…In the last decade, many methods have been proposed to tackle the task of 3D reconstruction from a single image. However, the majority of these methods require supervisory signals which are hard to obtain in the real world and in the CSDM [17] CMR [16] VPL [18] CSM [24] A-CSM [23] IMR [47] U-CMR [7] UMR [28] Ours wild, such as 3D models [3,6,58,33,50,40,55,1,26] or multi-view image collections [45,56,9,52,48,46,15,29].…”

Section: Related Workmentioning

confidence: 99%

“…Other methods that make use of mesh subdivision (e.g. [50,26]) need architectural changes that drastically increase the required memory and the inference time. On the contrary, our method is not heavily affected by the mesh subdivision operation and does not require any architectural changes, thanks to the per-vertex prediction of the deformation network.…”

Section: Multi-category Mesh Reconstructionmentioning

confidence: 99%

Multi-Category Mesh Reconstruction From Image Collections

Simoni¹,

Pini²,

Vezzani³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recently, learning frameworks have shown the capability of inferring the accurate shape, pose, and texture of an object from a single RGB image. However, current methods are trained on image collections of a single category in order to exploit specific priors, and they often make use of category-specific 3D templates. In this paper, we present an alternative approach that infers the textured mesh of objects combining a series of deformable 3D models and a set of instance-specific deformation, pose, and texture. Differently from previous works, our method is trained with images of multiple object categories using only foreground masks and rough camera poses as supervision. Without specific 3D templates, the framework learns category-level models which are deformed to recover the 3D shape of the depicted object. The instance-specific deformations are predicted independently for each vertex of the learned 3D mesh, enabling the dynamic subdivision of the mesh during the training process. Experiments show that the proposed framework can distinguish between different object categories and learn category-specific shape priors in an unsupervised manner. Predicted shapes are smooth and can leverage from multiple steps of subdivision during the training process, obtaining comparable or state-of-the-art results on two public datasets. Models and code are publicly released 1 .

show abstract