Self-organizing tree models for image synthesis

Pałubicki, Wojciech; Horel, Kipp; Longay, Steven; Runions, Adam; Lane, Brendan; Mĕch, Radomír; Prusinkiewicz, Przemysław

doi:10.1145/1576246.1531364

Cited by 55 publications

(73 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, Palubicki et al (2009) proposed a technique for generating realistic models of temperate-climate trees and shrubs. Their technique is based on the competition of buds and branches for light or space.…”

Section: Modeling Environmental Effectsmentioning

confidence: 99%

Image-Based Modeling of Plants and Trees

Kang¹,

Quan²

2009

Synthesis Lectures on Computer Vision

View full text Add to dashboard Cite

Plants and trees are among the most complex natural objects. Much work has been done attempting to model them, with varying degrees of success. In this book, we review the various approaches in computer graphics, which we categorize as rule-based, image-based, and sketch-based methods.We describe our approaches for modeling plants and trees using images. Image-based approaches have the distinct advantage that the resulting model inherits the realistic shape and complexity of a real plant or tree. We use different techniques for modeling plants (with relatively large leaves) and trees (with relatively small leaves). With plants, we model each leaf from images, while for trees, the leaves are only approximated due to their small size and large number. Both techniques start with the same initial step of structure from motion on multiple images of the plant or tree that is to be modeled.For our plant modeling system, because we need to model the individual leaves, these leaves need to be segmented out from the images. We designed our plant modeling system to be interactive, automating the process of shape recovery while relying on the user to provide simple hints on segmentation. Segmentation is performed in both image and 3D spaces, allowing the user to easily visualize its effect immediately. Using the segmented image and 3D data, the geometry of each leaf is then automatically recovered from the multiple views by fitting a deformable leaf model. Our system also allows the user to easily reconstruct branches in a similar manner.To model trees, because of the large leaf count, small image footprint, and widespread occlusions, we do not model the leaves exactly as we do for plants. Instead, we populate the tree with leaf replicas from segmented source images to reconstruct the overall tree shape. In addition, we use the shape patterns of visible branches to predict those of obscured branches. As a result, we are able to design our tree modeling system so as to minimize user intervention.We also handle the special case of modeling a tree from only a single image. Here, the user is required to draw strokes on the image to indicate the tree crown (so that the leaf region is approximately known) and to refine the recovery of branches. As before, we concatenate the shape patterns from a library to generate the 3D shape.To substantiate the effectiveness of our systems, we show realistic reconstructions of a variety of plants and trees from images. Finally, we offer our thoughts on improving our systems and on the remaining challenges associated with plant and tree modeling.

show abstract

Section: Modeling Environmental Effectsmentioning

confidence: 99%

Image-Based Modeling of Plants and Trees

Kang¹,

Quan²

2009

Synthesis Lectures on Computer Vision

View full text Add to dashboard Cite

show abstract

“…Adjusting stochastic parameters to achieve realistic models requires intensive botanical knowledge [6]. Another approach consists in modeling plant irregularities as a result of the competition for space between the different organs of the plants [7]. In this case, the volume of a plant is specified by the user and a generative process grows a branching structure with branches competing between each other.…”

Section: Introductionmentioning

confidence: 99%

Realistic Plant Modeling from Images Based on Analysis-by-Synthesis

Guénard

Morin

Boudon

et al. 2014

Mathematical Methods for Curves and Surfaces

View full text Add to dashboard Cite

OATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible. This is an author-deposited version published in : http://oatao.univ-toulouse.fr/ Eprints ID : 12497 Abstract. Plants are essential elements of virtual worlds to get pleasant and realistic 3D environments. Even if mature computer vision techniques allow the reconstruction of challenging 3D objects from images, due to high complexity of plant topology, dedicated methods for generating 3D plant models must be devised. We propose an analysis-bysynthesis method which generates 3D models of a plant from both images and a priori knowledge of the plant species. Our method is based on a skeletonisation algorithm which allows to generate a possible skeleton from a foliage segmentation. Then, we build a 3D generative model, based on a parametric model of branching systems that takes into account botanical knowledge. This method extends previous works by constraining the resulting skeleton to follow a natural branching structure. A first instance of a 3D model is generated. A reprojection of this model is compared with the original image. Then, we show that selecting the model from multiple proposals for the main branching structure of the plant and for the foliage improves the quality of the generated 3D model. Varying parameter values of the generative model, we produce a series of candidate models. A criterion based on comparing 3D virtual plant reprojection with the original image selects the best model. Finally, results on different species of plants illustrate the performance of the proposed method.

show abstract

“…We present a general procedure for obtaining these morphological clones. Although we opted 22 vs. self-organizing (Sachs and Novoplansky, 1995;Palubicki et al, 2009) character of architecture 48 development). 49 50 However, the most promising plant architectural models are so called functional-structural plant 51 models (FSPM), also known as "virtual plants" (Room et al, 1996;Sievänen et al, 2000; Godin et al, 52 2004), because this type of models allows for a balanced description between morphological and 53 functional/physiological properties of a plant.…”

mentioning

confidence: 99%

“…66Recently, we have reported a proof-of-concept study where we used reconstruction of a pine tree and 100 the corresponding FSPM (named LIGNUM (Perttunen et al, 1996; Sievanen et al, 2008)) to 101 demonstrate the practical feasibility of the approach (Potapov et al, 2016). In this work, however, we 102 develop a unifying interface for our procedure and use general-purpose fast procedural tree growth 103 model from (Palubicki et al, 2009), since such a simple procedural model is easier to adapt (it is 104 simple, fast, and efficient) for technical experimentation with the whole algorithm. Additionally, 105 similar algorithmic pipeline was reported in (Stava et al, 2014) for procedural tree growth models in 106 the context of graphics synthesis.…”

mentioning

confidence: 99%

“…39 40 Modeling plant architecture is approached from many directions. Some progress has been achieved in 41 synthesis of realistic plant forms in the field of computer graphics (Palubicki et al, 2009;Pirk et al, 42 2012; Stava et al, 2014). These models, although based on heuristic rules of growth, produce realistic 43 shape outcomes in a fast and efficient manner, which is usually dictated by the application of this 44 approach, that is natural sceneries in computer visualization.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A generator of morphological clones for plant species

Potapov

Järvenpää

Åkerblom

et al. 2017

Preprint

View full text Add to dashboard Cite

Correspondence: ilya.potapov@tut.fi 7 Keywords: stochastic structure tree model; quantitative structure tree model; morphological clone; 8 terrestrial laser scanning 9 10 Summary Statement. 11We present an algorithmic framework, based on the Bayesian inference, for generating morphological 12 tree clones using a combination of stochastic growth models and experimentally derived tree 13 structures. 14 15 Abstract. 16Detailed and realistic tree form generators have numerous applications in ecology and forestry. Here, 17we present an algorithm for generating morphological tree "clones" based on the detailed 18 reconstruction of the laser scanning data, statistical measure of similarity, and a plant growth algorithm 19 with simple stochastic rules. The algorithm is designed to produce tree forms, i.e. morphological 20 clones, similar as a whole (coarse-grain scale), but varying in minute details of organization (fine-grain 21 scale). We present a general procedure for obtaining these morphological clones. Although we opted 22 vs. self-organizing (Sachs and Novoplansky, 1995;Palubicki et al., 2009) character of architecture 48 development). 49 50 However, the most promising plant architectural models are so called functional-structural plant 51 models (FSPM), also known as "virtual plants" (Room et al., 1996;Sievänen et al., 2000; Godin et al., 52 2004), because this type of models allows for a balanced description between morphological and 53 functional/physiological properties of a plant. Thus, it is capable of connecting the external abiotic 54 factors (e.g. radiation, temperature and soil) and the most vital functions of a plant organism (such as 55 photosynthesis, respiration, and water and salts uptake) with its structural characteristics 56 (Prusinkiewicz, 2004;Fourcaud et al., 2008). 57 58 Nevertheless, biologically relevant architectural plant models rely on data in a form of empirically 59 fitted functions and parameters that correspond to a particular species and/or certain site conditions 60 (Mäkelä and Hari, 1986;Rauscher et al, 1990;Perttunen et al., 1996;Lacointe, 2000). Thus, the 61 change in these conditions requires re-calibration of the models, which is done in a manual fashion 62 every time the model is simulated for the new conditions. Strong dependence on data, where each 63 simulation would be calibrated automatically by data, is limited by both computation time and lack of 64 the fast measurement and processing systems allowing for a detailed 3D morphological reconstruction 65 of the real plant/tree. 66Recently, we have reported a proof-of-concept study where we used reconstruction of a pine tree and 100 the corresponding FSPM (named LIGNUM (Perttunen et al., 1996; Sievanen et al., 2008)) to 101 demonstrate the practical feasibility of the approach (Potapov et al., 2016). In this work, however, we 102 develop a unifying interface for our procedure and use general-purpose fast procedural tree growth 103 model from (Palubicki et al., 2009), since such a simple procedural model is easier to ada...

show abstract

Self-organizing tree models for image synthesis

Cited by 55 publications

References 48 publications

Image-Based Modeling of Plants and Trees

Image-Based Modeling of Plants and Trees

Realistic Plant Modeling from Images Based on Analysis-by-Synthesis

A generator of morphological clones for plant species

Contact Info

Product

Resources

About