Activity
-
We recently made SAM 2 twice as fast on Sieve. However, the model is a bit complex, so the amazing Jacob Marshall made a simple colab notebook that…
We recently made SAM 2 twice as fast on Sieve. However, the model is a bit complex, so the amazing Jacob Marshall made a simple colab notebook that…
Liked by Mokshith Voodarla
-
We're going to be at IBC 2024 in Amsterdam next month! If you're going also, shoot me a DM me and let's find time to connect around all things video…
We're going to be at IBC 2024 in Amsterdam next month! If you're going also, shoot me a DM me and let's find time to connect around all things video…
Liked by Mokshith Voodarla
-
This year is my first IBC and I’d love to meet everyone else who’ll be there as well! Fun fact: I’ve never been to Europe so it’ll also be my first…
This year is my first IBC and I’d love to meet everyone else who’ll be there as well! Fun fact: I’ve never been to Europe so it’ll also be my first…
Shared by Mokshith Voodarla
Experience
-
-
-
-
-
-
-
-
-
-
-
-
-
Education
Publications
-
S-BEV: Semantic Birds-Eye View Representation for Weather and Lighting Invariant 3-DoF Localization
arXiv preprint arXiv:2101.09569
See publicationWe describe a light-weight, weather and lighting invariant, Semantic Bird's Eye View (S-BEV) signature for vision-based vehicle re-localization. A topological map of S-BEV signatures is created during the first traversal of the route, which are used for coarse localization in subsequent route traversal. A fine-grained localizer is then trained to output the global 3-DoF pose of the vehicle using its S-BEV and its coarse localization. We conduct experiments on vKITTI2 virtual dataset and show…
We describe a light-weight, weather and lighting invariant, Semantic Bird's Eye View (S-BEV) signature for vision-based vehicle re-localization. A topological map of S-BEV signatures is created during the first traversal of the route, which are used for coarse localization in subsequent route traversal. A fine-grained localizer is then trained to output the global 3-DoF pose of the vehicle using its S-BEV and its coarse localization. We conduct experiments on vKITTI2 virtual dataset and show the potential of the S-BEV to be robust to weather and lighting. We also demonstrate results with 2 vehicles on a 22 km long highway route in the Ford AV dataset.
Languages
-
English
Native or bilingual proficiency
-
Telugu
Native or bilingual proficiency
-
Spanish
Limited working proficiency
More activity by Mokshith
-
Our team will be at IBC this year! Set up some time to chat about all things AI x video. Meeting booking link in comments.
Our team will be at IBC this year! Set up some time to chat about all things AI x video. Meeting booking link in comments.
Liked by Mokshith Voodarla
-
Introducing SAM2 on Sieve! Same amazing model but 2x faster than other providers and with zero degradation in quality 🔥 Unlike LLMs, video models…
Introducing SAM2 on Sieve! Same amazing model but 2x faster than other providers and with zero degradation in quality 🔥 Unlike LLMs, video models…
Liked by Mokshith Voodarla
-
Introducing SAM2 on Sieve! Same amazing model but 2x faster than other providers and with zero degradation in quality 🔥 Unlike LLMs, video models…
Introducing SAM2 on Sieve! Same amazing model but 2x faster than other providers and with zero degradation in quality 🔥 Unlike LLMs, video models…
Shared by Mokshith Voodarla
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More