SPIDR: SDF-based Neural Point Fields for Illumination and Deformation

no code implementations • 15 Oct 2022 • Ruofan Liang, Jiahao Zhang, Haoda Li, Chen Yang, Yushi Guan, Nandita Vijaykumar

To enable more accurate illumination updates after deformation, we use the shadow mapping technique to approximate the light visibility updates caused by geometry editing.

3D Reconstruction Lighting Estimation +2

Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors

no code implementations • CVPR 2022 • Yun-Chun Chen, Haoda Li, Dylan Turpin, Alec Jacobson, Animesh Garg

While the majority of existing part assembly methods focus on correctly posing semantic parts to recreate a whole object, we interpret assembly more literally: as mating geometric parts together to achieve a snug fit.

Object Point Cloud Registration

Decompose the Sounds and Pixels, Recompose the Events

no code implementations • 21 Dec 2021 • Varshanth R. Rao, Md Ibrahim Khalil, Haoda Li, Peng Dai, Juwei Lu

In this paper, we propose a framework centering around a novel architecture called the Event Decomposition Recomposition Network (EDRNet) to tackle the Audio-Visual Event (AVE) localization problem in the supervised and weakly supervised settings.