Zobrazeno 1 - 10
of 1 258
pro vyhledávání: '"Johnson, Justin"'
Autor:
Korovina, Nadezhda V., OSullivan, Shea, Kelm, Jennica, Lin, Yunhui L., Lloyd, Katherine, Johnson, Justin C.
Endothermic singlet fission (SF), an exciton multiplication process that produces a pair of high-energy triplet excitons (T1T1), is appealing for photovoltaic or photoelectrochemical applications, as it allows the conversion of entropy into electroni
Externí odkaz:
http://arxiv.org/abs/2409.17393
Contemporary 3D research, particularly in reconstruction and generation, heavily relies on 2D images for inputs or supervision. However, current designs for these 2D-3D mapping are memory-intensive, posing a significant bottleneck for existing method
Externí odkaz:
http://arxiv.org/abs/2404.19760
Autor:
Banani, Mohamed El, Raj, Amit, Maninis, Kevis-Kokitsi, Kar, Abhishek, Li, Yuanzhen, Rubinstein, Michael, Sun, Deqing, Guibas, Leonidas, Johnson, Justin, Jampani, Varun
Recent advances in large-scale pretraining have yielded visual foundation models with strong capabilities. Not only can recent models generalize to arbitrary images for their training task, their intermediate representations are useful for other visu
Externí odkaz:
http://arxiv.org/abs/2404.08636
Scalable annotation approaches are crucial for constructing extensive 3D-text datasets, facilitating a broader range of applications. However, existing methods sometimes lead to the generation of hallucinated captions, compromising caption quality. T
Externí odkaz:
http://arxiv.org/abs/2404.07984
We present PointInfinity, an efficient family of point cloud diffusion models. Our core idea is to use a transformer-based architecture with a fixed-size, resolution-invariant latent representation. This enables efficient training with low-resolution
Externí odkaz:
http://arxiv.org/abs/2404.03566
The Common Objects in Context (COCO) dataset has been instrumental in benchmarking object detectors over the past decade. Like every dataset, COCO contains subtle errors and imperfections stemming from its annotation procedure. With the advent of hig
Externí odkaz:
http://arxiv.org/abs/2403.18819
Autor:
Rockwell, Chris, Kulkarni, Nilesh, Jin, Linyi, Park, Jeong Joon, Johnson, Justin, Fouhey, David F.
Estimating relative camera poses between images has been a central problem in computer vision. Methods that find correspondences and solve for the fundamental matrix offer high precision in most cases. Conversely, methods predicting pose directly usi
Externí odkaz:
http://arxiv.org/abs/2403.03221
Autor:
Lubert-Perquel, Daphné, Cho, Byeong Wook, Philips, Alan J., Lee, Young Hee, Blackburn, Jeffrey L., Johnson, Justin C.
Combining the synthetic tunability of molecular compounds with the optical selection rules of transition metal dichalcogenides (TMDC) that derive from spin-valley coupling could provide interesting opportunities for the readout of quantum information
Externí odkaz:
http://arxiv.org/abs/2310.06979
Autor:
Kulkarni, Nilesh, Rempe, Davis, Genova, Kyle, Kundu, Abhijit, Johnson, Justin, Fouhey, David, Guibas, Leonidas
We address the problem of generating realistic 3D motions of humans interacting with objects in a scene. Our key idea is to create a neural interaction field attached to a specific object, which outputs the distance to the valid interaction manifold
Externí odkaz:
http://arxiv.org/abs/2307.07511
We introduce a method that can learn to predict scene-level implicit functions for 3D reconstruction from posed RGBD data. At test time, our system maps a previously unseen RGB image to a 3D reconstruction of a scene via implicit functions. While imp
Externí odkaz:
http://arxiv.org/abs/2306.08671