Kanle Shi

Kanle Shi

Auto-generated profile, based on publicly available information

Kanle Shi

Kuaishou Technology, Beijing, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 December 2021 in Visual Computing for Industry, Biomedicine, and Art
Verified
Journal Article
Open access
PDF file
SZShuyao Zhou
Shuyao Zhou
TZTianqian Zhu
Tianqian Zhu
KSKanle Shi
Kanle Shi
YLYazi Li
Yazi Li
Wen ZhengWen Zheng
Wen Zheng
JYJunhai Yong
Junhai Yong
Light fields are vector functions that map the geometry of light rays to the corresponding plenoptic attributes. They describe the holographic information of scenes by representing the amount of light flowing in every direction through every point in space. The physical concept of light fields was first proposed in 1936, and light fields are becoming increasingly important in the field of computer graphics, especially with the fast growth of computing capacity as well as network bandwidth. In this article, light field imaging is reviewed from the following aspects with an emphasis on the achievements of the past five years: (1) depth estimation, (2) content editing, (3) image quality, (4) scene reconstruction and view synthesis, and (5) industrial products because the technologies of lights fields also intersect with industrial applications. State-of-the-art research has focused on light field acquisition, manipulation, and display. In addition, the research has extended from the laboratory to industry. According to these achievements and challenges, in the near future, the applications of light fields could offer more portability, accessibility, compatibility, and ability to visualize the world.

19 July 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
QLQing Li
Qing Li
HFHuifang Feng
Huifang Feng
KSKanle Shi
Kanle Shi
YGYue Gao
Yue Gao
Yi FangYi Fang
Yi Fang
ZHZhizhong Han
Zhizhong Han
We propose a novel method called SHS-Net for point cloud normal estimation by learning signed hyper surfaces, which can accurately predict normals with global consistent orientation from various point clouds. Almost all existing methods estimate oriented normals through a two-stage pipeline, i.e., unoriented normal estimation and normal orientation, and each step is implemented by a separate algorithm. However, previous methods are sensitive to parameter settings, resulting in poor results from point clouds with noise, density variations and complex geometries. In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner. The signed hyper surfaces are implicitly learned in a high-dimensional feature space where the local and global information is aggregated. Specifically, we introduce a patch encoding module and a shape encoding module to encode a 3D point cloud into a local latent code and a global latent code, respectively. Then, an attention-weighted normal prediction module is proposed as a decoder, which takes the local and global latent codes as input to predict oriented normals. Experimental results show that our algorithm outperforms the state-of-the-art methods in both unoriented and oriented normal estimation.

16 June 2024
Verified
Conference Paper
Closed access
JZJunsheng Zhou
Junsheng Zhou
WZWeiqi Zhang
Weiqi Zhang
BMBaorui Ma
Baorui Ma
KSKanle Shi
Kanle Shi
Yu-Shen LiuYu-Shen Liu
Yu-Shen Liu
ZHZhizhong Han
Zhizhong Han
Diffusion models have shown remarkable results for im-age generation, editing and inpainting. Recent works ex-plore diffusion models for 3D shape generation with neural implicit functions, i.e., signed distance function and occu-pancy function. However, they are limited to shapes with closed surfaces, which prevents them from generating di-verse 3D real-world contents containing open surfaces. In this work, we present UDiFF, a 3D diffusion model for unsigned distance fields (UDFs) which is capable to gener-ate textured 3D shapes with open surfaces from text conditions or unconditionally. Our key idea is to generate UDFs in spatial-frequency domain with an optimal wavelet trans-formation, which produces a compact representation space for UDF generation. Specifically, instead of selecting an appropriate wavelet transformation which requires expen-sive manual efforts and still leads to large information loss, we propose a data-driven approach to learn the optimal wavelet transformation for UDFs. We evaluate UDiFF to show our advantages by numerical and visual comparisons with the latest methods on widely used benchmarks. Page: https://weiqi-zhang.github.io/UDiFF.

10 December 2023
Verified
Conference Paper
Open access
QLQing Li
Qing Li
HFHuifang Feng
Huifang Feng
KSKanle Shi
Kanle Shi
Yi FangYi Fang
Yi Fang
Yu-Shen LiuYu-Shen Liu
Yu-Shen Liu
ZHZhizhong Han
Zhizhong Han
We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation. It has excellent gradient approximation properties for the underlying geometry of the data. We utilize a simple neural network to parameterize the objective function to produce gradients at points using a global implicit representation. However, the derived gradients usually drift away from the ground-truth oriented normals due to the lack of local detail descriptions. Therefore, we introduce Gradient Vector Optimization (GVO) to learn an angular distance field based on local plane geometry to refine the coarse gradient vectors. Finally, we formulate our method with a two-phase pipeline of coarse estimation followed by refinement. Moreover, we integrate two weighting functions, i.e., anisotropic kernel and inlier score, into the optimization to improve the robust and detail-preserving performance. Our method efficiently conducts global gradient approximation while achieving better accuracy and generalization ability of local feature description. This leads to a state-of-the-art normal estimator that is robust to noise, outliers and point density variations. Extensive evaluations show that our method outperforms previous works in both unoriented and oriented normal estimation on widely used benchmarks. The source code and pre-trained models are available at https://github.com/LeoQLi/NGLO .


14 January 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
WZWenyuan Zhang
Wenyuan Zhang
CWChunsheng Wang
Chunsheng Wang
KSKanle Shi
Kanle Shi
Yu-Shen LiuYu-Shen Liu
Yu-Shen Liu
ZHZhizhong Han
Zhizhong Han
Unsigned distance functions (UDFs) have been a vital representation for open surfaces. With different differentiable renderers, current methods are able to train neural networks to infer a UDF by minimizing the rendering errors with the UDF to the multi-view ground truth. However, these differentiable renderers are mainly handcrafted, which makes them either biased on ray-surface intersections, or sensitive to unsigned distance outliers, or not scalable to large scenes. To resolve these issues, we present a novel differentiable renderer to infer UDFs more accurately. Instead of using handcrafted equations, our differentiable renderer is a neural network which is pre-trained in a data-driven manner. It learns how to render unsigned distances into depth images, leading to a prior knowledge, dubbed volume rendering priors. To infer a UDF for an unseen scene from multiple RGB images, we generalize the learned volume rendering priors to map inferred unsigned distances in alpha blending for RGB image rendering. To reduce the bias of sampling in UDF inference, we utilize an auxiliary point sampling prior as an indicator of ray-surface intersection, and propose novel schemes towards more accurate and uniform sampling near the zero-level sets. We also propose a new strategy that leverages our pretrained volume rendering prior to serve as a general surface refiner, which can be integrated with various Gaussian reconstruction methods to optimize the Gaussian distributions and refine geometric details. Our results show that the learned volume rendering prior is unbiased, robust, scalable, 3D aware, and more importantly, easy to learn. Further experiments show that the volume rendering prior is also a general strategy to enhance other neural implicit representations such as signed distance function and occupancy. We evaluate our method on both widely used benchmarks and real scenes, and report superior performance over the state-of-the-art methods.