Zobrazeno 1 - 10
of 2 147
pro vyhledávání: '"Hold, A"'
Autor:
Yoon, Jae Shin, Shu, Zhixin, Ren, Mengwei, Zhang, Xuaner, Hold-Geoffroy, Yannick, Singh, Krishna Kumar, Zhang, He
We introduce a high-fidelity portrait shadow removal model that can effectively enhance the image of a portrait by predicting its appearance under disturbing shadows and highlights. Portrait shadow removal is a highly ill-posed problem where multiple
Externí odkaz:
http://arxiv.org/abs/2410.05525
Autor:
Hou, Andrew, Shu, Zhixin, Zhang, Xuaner, Zhang, He, Hold-Geoffroy, Yannick, Yoon, Jae Shin, Liu, Xiaoming
Existing portrait relighting methods struggle with precise control over facial shadows, particularly when faced with challenges such as handling hard shadows from directional light sources or adjusting shadows while remaining in harmony with existing
Externí odkaz:
http://arxiv.org/abs/2408.13922
Autor:
Dastjerdi, Mohammad Reza Karimi, Fortier-Chouinard, Frédéric, Hold-Geoffroy, Yannick, Hébert, Marc, Demers, Claude, Kalantari, Nima, Lalonde, Jean-François
Most novel view synthesis methods such as NeRF are unable to capture the true high dynamic range (HDR) radiance of scenes since they are typically trained on photos captured with standard low dynamic range (LDR) cameras. While the traditional exposur
Externí odkaz:
http://arxiv.org/abs/2407.06150
Autor:
Zeng, Zheng, Deschaintre, Valentin, Georgiev, Iliyan, Hold-Geoffroy, Yannick, Hu, Yiwei, Luan, Fujun, Yan, Ling-Qi, Hašan, Miloš
Publikováno v:
SIGGRAPH Conference Papers '24, July 27-August 1, 2024, Denver, CO, USA
The three areas of realistic forward rendering, per-pixel inverse rendering, and generative image synthesis may seem like separate and unrelated sub-fields of graphics and vision. However, recent work has demonstrated improved estimation of per-pixel
Externí odkaz:
http://arxiv.org/abs/2405.00666
We introduce LightIt, a method for explicit illumination control for image generation. Recent generative methods lack lighting control, which is crucial to numerous artistic aspects of image generation such as setting the overall mood or cinematic ap
Externí odkaz:
http://arxiv.org/abs/2403.10615
Scene-based spatial audio formats, such as Ambisonics, are playback system agnostic and may therefore be favoured for delivering immersive audio experiences to a wide range of (potentially unknown) devices. The number of channels required to deliver
Externí odkaz:
http://arxiv.org/abs/2401.13401
In this paper, we elaborate on correctly predicting \'Echelle spectrograms by employing the fully three-dimensional representation of Snell's law to model the effects of prisms as cross-dispersers in \'Echelle spectrographs. We find that it is not su
Externí odkaz:
http://arxiv.org/abs/2401.00105
Autor:
Giroux, Justine, Dastjerdi, Mohammad Reza Karimi, Hold-Geoffroy, Yannick, Vazquez-Corral, Javier, Lalonde, Jean-François
Progress in lighting estimation is tracked by computing existing image quality assessment (IQA) metrics on images from standard datasets. While this may appear to be a reasonable approach, we demonstrate that doing so does not correlate to human pref
Externí odkaz:
http://arxiv.org/abs/2312.04334
Autor:
Pandey, Karran, Guerrero, Paul, Gadelha, Matheus, Hold-Geoffroy, Yannick, Singh, Karan, Mitra, Niloy
Diffusion Handles is a novel approach to enabling 3D object edits on diffusion images. We accomplish these edits using existing pre-trained diffusion models, and 2D image depth estimation, without any fine-tuning or 3D object retrieval. The edited re
Externí odkaz:
http://arxiv.org/abs/2312.02190
Autor:
Zhou, Xilong, Hašan, Miloš, Deschaintre, Valentin, Guerrero, Paul, Hold-Geoffroy, Yannick, Sunkavalli, Kalyan, Kalantari, Nima Khademi
Publikováno v:
Siggraph 2023
Authoring high-quality digital materials is key to realism in 3D rendering. Previous generative models for materials have been trained exclusively on synthetic data; such data is limited in availability and has a visual gap to real materials. We circ
Externí odkaz:
http://arxiv.org/abs/2305.12296