Search for: All records

Recent advances in monocular depth estimation have been made by incorporating natural language as additional guidance. Although yielding impressive results the impact of the language prior particularly in terms of generalization and robustness remains unexplored. In this paper we address this gap by quantifying the impact of this prior and introduce methods to benchmark its effectiveness across various settings. We generate "low-level" sentences that convey object-centric three-dimensional spatial relationships incorporate them as additional language priors and evaluate their downstream impact on depth estimation. Our key finding is that current language-guided depth estimators perform optimally only with scene-level descriptions and counter-intuitively fare worse with low level descriptions. Despite leveraging additional data these methods are not robust to directed adversarial attacks and decline in performance with an increase in distribution shift. Finally to provide a foundation for future research we identify points of failures and offer insights to better understand these shortcomings. With an increasing number of methods using language for depth estimation our findings highlight the opportunities and pitfalls that require careful consideration for effective deployment in real-world settings. 

The paper provides a description of the ideas behind the DiSProD algorithm and system variants that participated and was the winner in the International Probabilistic Planning Competition, 2023. 

Low‐frequency (Interannual and longer timescale) variability in sea surface temperature (SST) of the Indian Ocean plays a crucial role in affecting the regional climate. Using a high‐resolution global model simulation, we show that internal oceanic variability is an important cause of the observed low‐frequency variability in the subtropical‐midlatitude south Indian Ocean (SIO) between 20° and 40°S, a marked southward shift in the latitude band of active internal variability for the low‐frequency compared to earlier estimates based on coarser Indian Ocean regional models. Notably, we show that internal variability does not contribute to the observed low‐frequency variability in the Seychelles−Chagos thermocline ridge region. Energy budget analysis shows that baroclinic instability is the primary cause for the internal variability. The slowly growing baroclinic instabilities at low frequency and longer length scale favor Rossby waves' generation, propagating the SST and sea level anomaly signals westward.