Kennard Yanting Chan

Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning

Bohan Wang, Zhongqi Yue, Fengda Zhang, Liqi Bi et autres

We completely discard the conventional spatial prior in image representation and introduce a novel discrete visual tokenizer: Self-consistency Tokenizer (Selftok). At its design core, we compose an autoregressive (AR) prior -- mirroring the causal structure of language -- into visual tokens by …

3DFG-PIFu: 3D Feature Grids for Human Digitization from Sparse Views

Kennard Yanting Chan, Fayao Liu, Guosheng Lin, Chuan-Sheng Foo et autres

sg (code pays fourni par la source)

R-Cyclic Diffuser: Reductive and Cyclic Latent Diffusion for 3D Clothed Human Digitalization

Kennard Yanting Chan, Fayao Liu, Guosheng Lin, Chuan-Sheng Foo et autres

Recently, the authors of Zero-1-to-3 demonstrated that a latent diffusion model, pretrained with Internet-scale data, can not only address the single-view 3D object reconstruction task but can even attain SOTA results in it. However, when applied to the task of single-view 3D …

sg (code pays fourni par la source)

Fine Structure-Aware Sampling: A New Sampling Training Scheme for Pixel-Aligned Implicit Models in Single-View Human Reconstruction

Kennard Yanting Chan, Fayao Liu, Guosheng Lin, Chuan-Sheng Foo et autres

Pixel-aligned implicit models, such as PIFu, PIFuHD, and ICON, are used for single-view clothed human reconstruction. These models need to be trained using a sampling training scheme. Existing sampling training schemes either fail to capture thin surfaces (e.g. ears, fingers) or cause …

sg (code pays fourni par la source)

IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-view Human Reconstruction

Kennard Yanting Chan, Guosheng Lin, Haiyu Zhao, Weisi Lin

We propose IntegratedPIFu, a new pixel aligned implicit model that builds on the foundation set by PIFuHD. IntegratedPIFu shows how depth and human parsing information can be predicted and capitalised upon in a pixel-aligned implicit model. In addition, IntegratedPIFu introduces depth oriented …

IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-View Human Reconstruction

Kennard Yanting Chan, Guosheng Lin, Haiyu Zhao, Weisi Lin

sg (code pays fourni par la source)

Dense 3D Reconstruction for Visual Tunnel Inspection using Unmanned\n Aerial Vehicle

Ramanpreet Singh Pahwa, Kennard Yanting Chan, Jiamin Bai, Vincensius Billy Saputra et autres

Advances in Unmanned Aerial Vehicle (UAV) opens venues for application such\nas tunnel inspection. Owing to its versatility to fly inside the tunnels, it\ncan quickly identify defects and potential problems related to safety. However,\nlong tunnels, especially with repetitive or uniform structures pose a\nsignificant …

Dense 3D Reconstruction for Visual Tunnel Inspection using Unmanned Aerial Vehicle

Ramanpreet Singh Pahwa, Kennard Yanting Chan, Jiamin Bai, Vincensius Billy Saputra et autres

Advances in Unmanned Aerial Vehicle (UAV) opens venues for application such as tunnel inspection. Owing to its versatility to fly inside the tunnels, it can quickly identify defects and potential problems related to safety. However, long tunnels, especially with repetitive or uniform …

sg, us (code pays fourni par la source)