2 papers
cs.CV2023
Reconstructing Animatable Categories from Videos
Gengshan Yang, Chaoyang Wang, N Dinesh Reddy +1
Building animatable 3D models is challenging due to the need for 3D scans, laborious registration, and manual rigging, which are difficult to scale to arbitrary categories. Recentl…
cs.CV2023
3D-aware Conditional Image Synthesis
Kangle Deng, Gengshan Yang, Deva Ramanan +1
We propose pix2pix3D, a 3D-aware conditional generative model for controllable photorealistic image synthesis. Given a 2D label map, such as a segmentation or edge map, our model l…