Vatsal Agarwal

Vatsal Agarwal

Auto-generated profile, based on publicly available information

Vatsal Agarwal

University of Maryland

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 November 2024
Verified
Book Chapter
Closed access
PDF file
SMSoumik Mukhopadhyay
Soumik Mukhopadhyay
MGMatthew Gwilliam
Matthew Gwilliam
YYYosuke Yamaguchi
Yosuke Yamaguchi
VAVatsal Agarwal
Vatsal Agarwal
NPNamitha Padmanabhan
Namitha Padmanabhan
ASAbhinav Shrivastava
Abhinav Shrivastava

29 October 2024
Verified
Book Chapter
Closed access
PDF file
ASArchana Swaminathan
Archana Swaminathan
AGAnubhav Gupta
Anubhav Gupta
KGKamal Gupta
Kamal Gupta
SMShishira R. Maiya
Shishira R. Maiya
VAVatsal Agarwal
Vatsal Agarwal
ASAbhinav Shrivastava
Abhinav Shrivastava

10 September 2024 in arXiv
Verified
Preprint
Open access
PDF file
ASArchana Swaminathan
Archana Swaminathan
AGAnubhav Gupta
Anubhav Gupta
KGKamal Gupta
Kamal Gupta
SMShishira R. Maiya
Shishira R. Maiya
VAVatsal Agarwal
Vatsal Agarwal
ASAbhinav Shrivastava
Abhinav Shrivastava
Neural Radiance Fields (NeRFs) have revolutionized the reconstruction of static scenes and objects in 3D, offering unprecedented quality. However, extending NeRFs to model dynamic objects or object articulations remains a challenging problem. Previous works have tackled this issue by focusing on part-level reconstruction and motion estimation for objects, but they often rely on heuristics regarding the number of moving parts or object categories, which can limit their practical use. In this work, we introduce LEIA, a novel approach for representing dynamic 3D objects. Our method involves observing the object at distinct time steps or "states" and conditioning a hypernetwork on the current state, using this to parameterize our NeRF. This approach allows us to learn a view-invariant latent representation for each state. We further demonstrate that by interpolating between these states, we can generate novel articulation configurations in 3D space that were previously unseen. Our experimental results highlight the effectiveness of our method in articulating objects in a manner that is independent of the viewing angle and joint configuration. Notably, our approach outperforms previous methods that rely on motion information for articulation registration.