Zobrazeno 1 - 10
of 795
pro vyhledávání: '"Chang, P. X."'
We use the star formation rate-stellar mass relation ($SFR - {M_ * }$) of galaxies to measure their luminosity distances as well as estimate cosmological parameters. We obtain a sample of 341 high-redshift galaxies at $5 < z < 14$, and 51 others at $
Externí odkaz:
http://arxiv.org/abs/2412.01853
Reconstructing structured 3D scenes from RGB images using CAD objects unlocks efficient and compact scene representations that maintain compositionality and interactability. Existing works propose training-heavy methods relying on either expensive ye
Externí odkaz:
http://arxiv.org/abs/2411.19492
Autor:
Raychaudhuri, Sonia, Ta, Duy, Ashton, Katrina, Chang, Angel X., Wang, Jiuguang, Bucher, Bernadette
Landmark-based navigation (e.g. go to the wooden desk) and relative positional navigation (e.g. move 5 meters forward) are distinct navigation challenges solved very differently in existing robotics navigation methodology. We present a new dataset, O
Externí odkaz:
http://arxiv.org/abs/2411.07848
We address the challenge of creating 3D assets for household articulated objects from a single image. Prior work on articulated object creation either requires multi-view multi-state input, or only allows coarse control over the generation process. T
Externí odkaz:
http://arxiv.org/abs/2410.16499
Despite much progress in large 3D datasets there are currently few interactive 3D object datasets, and their scale is limited due to the manual effort required in their construction. We introduce the static to openable (S2O) task which creates intera
Externí odkaz:
http://arxiv.org/abs/2409.18896
Autor:
Meeussen, A. S., Bordiga, G., Chang, A. X., Spoettling, B., Becker, K. P., Mahadevan, L., Bertoldi, K.
Mechanical metamaterials -- structures with unusual properties that emerge from their internal architecture -- that are designed to undergo large deformations typically exploit large internal rotations, and therefore, necessitate the incorporation of
Externí odkaz:
http://arxiv.org/abs/2408.16059
We introduce a new approach for generating realistic 3D models with UV maps through a representation termed "Object Images." This approach encapsulates surface geometry, appearance, and patch structures within a 64x64 pixel image, effectively convert
Externí odkaz:
http://arxiv.org/abs/2408.03178
Despite advances in text-to-3D generation methods, generation of multi-object arrangements remains challenging. Current methods exhibit failures in generating physically plausible arrangements that respect the provided text description. We present Sc
Externí odkaz:
http://arxiv.org/abs/2408.02211
Autor:
Gharaee, Zahra, Lowe, Scott C., Gong, ZeMing, Arias, Pablo Millan, Pellegrino, Nicholas, Wang, Austin T., Haurum, Joakim Bruslund, Zarubiieva, Iuliia, Kari, Lila, Steinke, Dirk, Taylor, Graham W., Fieguth, Paul, Chang, Angel X.
As part of an ongoing worldwide effort to comprehend and monitor insect biodiversity, this paper presents the BIOSCAN-5M Insect dataset to the machine learning community and establish several benchmark tasks. BIOSCAN-5M is a comprehensive dataset con
Externí odkaz:
http://arxiv.org/abs/2406.12723
We introduce Duoduo CLIP, a model for 3D representation learning that learns shape encodings from multi-view images instead of point-clouds. The choice of multi-view images allows us to leverage 2D priors from off-the-shelf CLIP models to facilitate
Externí odkaz:
http://arxiv.org/abs/2406.11579