Projects per year
Learning object-centric scene representations is essential for attaining structural understanding and abstraction of complex scenes. Yet, as current approaches for unsupervised object-centric representation learning are built upon either a stationary observer assumption or a static scene assumption, they often: i) suffer single-view spatial ambiguities, or ii) infer incorrectly or inaccurately object representations from dynamic scenes. To address this, we propose Dynamics-aware Multi-Object Network (DyMON), a method that broadens the scope of multi-view object-centric representation learning to dynamic scenes. We train DyMON on multi-view-dynamic-scene data and show that DyMON learns—without supervision—to factorize the entangled effects of observer motions and scene object dynamics from a sequence of observations, and constructs scene object spatial representations suitable for rendering at arbitrary times (querying across time) and from arbitrary viewpoints (querying across space). We also show that the factorized scene representations (w.r.t. objects) support querying about a single object by space and time independently.
|Title of host publication||Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021)|
|Publisher||Neural Information Processing Systems|
|Number of pages||26|
|Publication status||Published - 6 Dec 2021|
|Event||35th Conference on Neural Information Processing Systems - Virtual|
Duration: 6 Dec 2021 → 14 Dec 2021
|Name||Advances in Neural Information Processing Systems|
|Conference||35th Conference on Neural Information Processing Systems|
|Abbreviated title||NeurIPS 2021|
|Period||6/12/21 → 14/12/21|
FingerprintDive into the research topics of 'Object-Centric Representation Learning with Generative Spatial-Temporal Factorization'. Together they form a unique fingerprint.
- 1 Finished
TrimBot2020-A gardening robot for rose, hedge and topiary trimming (coordinating)
1/01/16 → 31/12/19