Browsing by Author "Kim, Young Min"

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    Auto-rigging 3D Bipedal Characters in Arbitrary Poses
    (The Eurographics Association, 2021) Kim, Jeonghwan; Son, Hyeontae; Bae, Jinseok; Kim, Young Min; Theisel, Holger and Wimmer, Michael
    We present an end-to-end algorithm that can automatically rig a given 3D character such that it is ready for 3D animation. The animation of a virtual character requires the skeletal motion defined with bones and joints, and the corresponding deformation of the mesh represented with skin weights. While the conventional animation pipeline requires the initial 3D character to be in the predefined default pose, our pipeline can rig a 3D character in arbitrary pose. We handle the increased ambiguity by fixing the skeletal topology and solving for the full deformation space. After the skeletal positions and orientations are fully discovered, we can deform the provided 3D character into the default pose, from which we can animate the character with the help of recent motion-retargeting techniques. Our results show that we can successfully animate initially deformed characters, which was not possible with previous works.
  • Thumbnail Image
    Item
    Fast and Lightweight Path Guiding Algorithm on GPU
    (The Eurographics Association, 2021) Kim, Juhyeon; Kim, Young Min; Lee, Sung-Hee and Zollmann, Stefanie and Okabe, Makoto and Wünsche, Burkhard
    We propose a simple, yet practical path guiding algorithm that runs on GPU. Path guiding renders photo-realistic images by simulating the iterative bounces of rays, which are sampled from the radiance distribution. The radiance distribution is often learned by serially updating the hierarchical data structure to represent complex scene geometry, which is not easily implemented with GPU. In contrast, we employ a regular data structure and allow fast updates by processing a significant number of rays with GPU. We further increase the efficiency of radiance learning by employing SARSA [SB18] used in reinforcement learning. SARSA does not include aggregation of incident radiance from all directions nor storing all of the previous paths. The learned distribution is then sampled with an optimized rejection sampling, which adapts the current surface normal to reflect finer geometry than the grid resolution. All of the algorithms have been implemented on GPU using megakernal architecture with NVIDIA OptiX [PBD*10]. Through numerous experiments on complex scenes, we demonstrate that our proposed path guiding algorithm works efficiently on GPU, drastically reducing the number of wasted paths.
  • No Thumbnail Available
    Item
    IBL-NeRF: Image-Based Lighting Formulation of Neural Radiance Fields
    (The Eurographics Association and John Wiley & Sons Ltd., 2023) Choi, Changwoon; Kim, Juhyeon; Kim, Young Min; Chaine, Raphaëlle; Deng, Zhigang; Kim, Min H.
    We propose IBL-NeRF, which decomposes the neural radiance fields (NeRF) of large-scale indoor scenes into intrinsic components. Recent approaches further decompose the baked radiance of the implicit volume into intrinsic components such that one can partially approximate the rendering equation. However, they are limited to representing isolated objects with a shared environment lighting, and suffer from computational burden to aggregate rays with Monte Carlo integration. In contrast, our prefiltered radiance field extends the original NeRF formulation to capture the spatial variation of lighting within the scene volume, in addition to surface properties. Specifically, the scenes of diverse materials are decomposed into intrinsic components for rendering, namely, albedo, roughness, surface normal, irradiance, and prefiltered radiance. All of the components are inferred as neural images from MLP, which can model large-scale general scenes. Especially the prefiltered radiance effectively models the volumetric light field, and captures spatial variation beyond a single environment light. The prefiltering aggregates rays in a set of predefined neighborhood sizes such that we can replace the costly Monte Carlo integration of global illumination with a simple query from a neural image. By adopting NeRF, our approach inherits superior visual quality and multi-view consistency for synthesized images as well as the intrinsic components. We demonstrate the performance on scenes with complex object layouts and light configurations, which could not be processed in any of the previous works.
  • Thumbnail Image
    Item
    IMAT: The Iterative Medial Axis Transform
    (© 2021 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd, 2021) Lee, Yonghyeon; Baek, Jonghyuk; Kim, Young Min; Park, Frank Chongwoo; Benes, Bedrich and Hauser, Helwig
    We present the iterative medial axis transform (IMAT), an iterative descent method that constructs a medial axis transform (MAT) for a sparse, noisy, oriented point cloud sampled from an object's boundary. We first establish the equivalence between the traditional definition of the MAT of an object, i.e., the set of centres and corresponding radii of all balls maximally inscribed inside the object, with an alternative characterization matching the boundary enclosing the union of the balls with the object boundary. Based on this boundary equivalence characterization, a new MAT algorithm is proposed, in which an error function that reflects the difference between the two boundaries is minimized while restricting the number of balls to within some a priori specified upper limit. An iterative descent method with guaranteed local convergence is developed for the minimization that is also amenable to parallelization. Both quantitative and qualitative analyses of diverse 2D and 3D objects demonstrate the noise robustness, shape fidelity, and representation efficiency of the resulting MAT.
  • Thumbnail Image
    Item
    Planar Abstraction and Inverse Rendering of 3D Indoor Environment
    (The Eurographics Association, 2019) Kim, Young Min; Ryu, Sangwoo; Kim, Ig-Jae; Cignoni, Paolo and Miguel, Eder
    A large-scale scanned 3D environment suffers from complex occlusions and misalignment errors. The reconstruction contains holes in geometry and ghosting in texture. These are easily noticed and cannot be used in visually compelling VR content without further processing. On the other hand, the well-known Manhattan World priors successfully recreate relatively simple or clean structures. In this paper, we would like to push the limit of planar representation in indoor environments. We use planes not only to represent the environment geometrically but also to solve an inverse rendering problem considering texture and light. The complex process of shape inference and intrinsic imaging is greatly simplified with the help of detected planes and yet produces a realistic 3D indoor environment. The produced content can effectively represent the spatial arrangements for various AR/VR applications and can be readily combined with virtual objects possessing plausible lighting and texture.
  • No Thumbnail Available
    Item
    Robust Novel View Synthesis with Color Transform Module
    (The Eurographics Association and John Wiley & Sons Ltd., 2023) Kim, Sang Min; Choi, Changwoon; Heo, Hyeongjun; Kim, Young Min; Chaine, Raphaëlle; Deng, Zhigang; Kim, Min H.
    The advancements of the Neural Radiance Field (NeRF) and its variants have demonstrated remarkable capabilities in generating photo-realistic novel views from a small set of input images. While recent works suggest various techniques and model architectures that enhance speed or reconstruction quality, little attention is paid to exploring the RGB color space of input images. In this paper, we propose a universal color transform module that can maximally harness the captured evidence for the neural networks at hand. The color transform module utilizes an encoder-decoder framework that maps the RGB color space into a new latent space, enhancing the expressiveness of the input domain. We attach the encoder and the decoder at the input and output of a NeRF model of choice, respectively, and jointly optimize them to maintain the cycle consistency of the proposed transform, in addition to minimizing the reconstruction errors in the feature domain. Our comprehensive experiments demonstrate that the learned color space can significantly improve the quality of reconstructions compared to the conventional RGB representation. Its benefits are particularly pronounced in challenging scenarios characterized by low-light environments and scenes with low-textured regions. The proposed color transform pushes the boundaries of limitations in the input domain and offers a promising avenue for advancing the reconstruction capabilities of various neural representations. Source code is available at https://github.com/sangminkim-99/ColorTransformModule.
  • No Thumbnail Available
    Item
    Text2PointCloud: Text-Driven Stylization for Sparse PointCloud
    (The Eurographics Association, 2023) Hwang, Inwoo; Kim, Hyeonwoo; Lim, Donggeun; Park, Inbum; Kim, Young Min; Babaei, Vahid; Skouras, Melina
    We present Text2PointCloud, a method to process sparse, noisy point cloud input and generate high-quality stylized output. Given point cloud data, our iterative pipeline stylizes and deforms points guided by a text description and gradually densifies the point cloud. As our framework utilizes the existing resources of image and text embedding, it does not require dedicated 3D datasets with high-quality textures, which are produced by skillful artists or high-resolution colored 3D models. Also, since we represent 3D shapes as a point cloud, we can visualize fine-grained geometric variations with a complex topology such as flowers or fire. To the best of our knowledge, it is the first approach for directly stylizing the uncolored, sparse point cloud input without converting it into a mesh or implicit representation, which might fail to express the original information in the measurements, especially when the object exhibits complex topology.