Загрузка видео...

Не удалось загрузить видео

На главную

SLAM algorithms struggle on endoscopy videos - specularity, textureless, & dynamic near-field lighting. We introduce a Near-Field Light Bundle Adjst. loss (NFL-BA): improves performance of SOTA SLAM, e.g. MonoGS (⬆️35% in tracking, ⬆️48% in mapping). See

SenguptRoni's profile picture

Roni Sengupta

2,610 subscribers

19,439 просмотров • 1 год назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 2

Фото профиля Roni Sengupta
Roni Sengupta1 год назад

Our NFL-BA loss relies on the fact that points closer to the camera (depth map) with orientations facing the camera (normal map) reflect more light. NFL-BA loss is minimized during the Tracking & Mapping phase of existing SLAM frameworks, results shown on 3DGS SLAMs.

Фото профиля Virtue of Selfish Investing (VoSI)
Virtue of Selfish Investing (VoSI)2 лет назад

Supercharge your profits using our time-tested, optimized, low risk buying strategies including Undercut & Rally, VooDoo low volume signatures, Buyable Gap-Ups and Pocket Pivots. We combine positive fundamentals with technical timing to stack the odds in your favor.

Похожие видео

🚀 Excited to attend my first #NeurIPS2025 and present our lighting-aware SLAM method, NFL-BA! 🔗 🔦 Why this matters: Traditional Bundle Adjustment (BA) in SLAM assumes static lighting, but many real scenarios—endoscopy, search & rescue, subterranean robotics—use co-located light + camera, creating dynamic, near-field lighting that breaks these assumptions. ✨ What we introduce: Near-Field Lighting Bundle Adjustment Loss (NFL-BA) — a formulation that explicitly models near-field illumination inside the BA objective, allowing SLAM systems to jointly reason about geometry, appearance, and lighting. 📈 Results: Modeling lighting directly leads to ~38% improvement in mapping & tracking across dynamic-lighting sequences in both endoscopy and indoor scenes. 🧩 Plug-and-play: NFL-BA integrates seamlessly into existing neural rendering–based SLAM pipelines, using both implicit (NeRF-style) or explicit (3DGS) scene representations. 🌟 If you’re interested in SLAM, neural rendering, or illumination modeling, come check it out on Friday's poster session, 11-2pm, #4407.
0:38

🚀 Excited to attend my first #NeurIPS2025 and present our lighting-aware SLAM method, NFL-BA! 🔗 🔦 Why this matters: Traditional Bundle Adjustment (BA) in SLAM assumes static lighting, but many real scenarios—endoscopy, search & rescue, subterranean robotics—use co-located light + camera, creating dynamic, near-field lighting that breaks these assumptions. ✨ What we introduce: Near-Field Lighting Bundle Adjustment Loss (NFL-BA) — a formulation that explicitly models near-field illumination inside the BA objective, allowing SLAM systems to jointly reason about geometry, appearance, and lighting. 📈 Results: Modeling lighting directly leads to ~38% improvement in mapping & tracking across dynamic-lighting sequences in both endoscopy and indoor scenes. 🧩 Plug-and-play: NFL-BA integrates seamlessly into existing neural rendering–based SLAM pipelines, using both implicit (NeRF-style) or explicit (3DGS) scene representations. 🌟 If you’re interested in SLAM, neural rendering, or illumination modeling, come check it out on Friday's poster session, 11-2pm, #4407.

Roni Sengupta

21,162 просмотров • 7 месяцев назад

vMAP: Vectorised Object Mapping for Neural Field SLAM abs: project page:
2:41

vMAP: Vectorised Object Mapping for Neural Field SLAM abs: project page:

AK

36,137 просмотров • 3 лет назад

GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels • We propose a 2D Gaussian-based incremental reconstruction strategy and a Surface-aware Depth Rendering mechanism. This approach effectively mitigates geometry distortions and improves tracking accuracy. • Our dense SLAM system features a front-end/back-end architecture and incorporates a local map design, ensuring tracking accuracy and efficiency. • We conduct extensive experiments demonstrating the superiority of our approach in both tracking accuracy and reconstruction quality compared to SOTA methods.
0:24

GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels • We propose a 2D Gaussian-based incremental reconstruction strategy and a Surface-aware Depth Rendering mechanism. This approach effectively mitigates geometry distortions and improves tracking accuracy. • Our dense SLAM system features a front-end/back-end architecture and incorporates a local map design, ensuring tracking accuracy and efficiency. • We conduct extensive experiments demonstrating the superiority of our approach in both tracking accuracy and reconstruction quality compared to SOTA methods.

MrNeRF

11,004 просмотров • 1 год назад

Grand slam on division 1 field!
0:48

Grand slam on division 1 field!

Andy Beshear

97,807 просмотров • 11 месяцев назад

Check out the Neural Graph Mapping for Dense SLAM with Efficient Loop Closure paper by Leonard Bruns, Jun Zhang, and Patric Jensfelt, visualized with Rerun. “Existing neural field-based SLAM methods typically employ a single monolithic field as their scene representation. This prevents efficient incorporation of loop closure constraints and limits scalability. To address these shortcomings, we propose a neural mapping framework which anchors lightweight neural fields to the pose graph of a sparse visual SLAM system.”
0:37

Check out the Neural Graph Mapping for Dense SLAM with Efficient Loop Closure paper by Leonard Bruns, Jun Zhang, and Patric Jensfelt, visualized with Rerun. “Existing neural field-based SLAM methods typically employ a single monolithic field as their scene representation. This prevents efficient incorporation of loop closure constraints and limits scalability. To address these shortcomings, we propose a neural mapping framework which anchors lightweight neural fields to the pose graph of a sparse visual SLAM system.”

Rerun

12,865 просмотров • 2 лет назад

"AN OPPOSITE FIELD GRAND SLAM FOR J.D. MARTINEZ!" Join Gary, Keith, & Ron in the booth for J.D. Martinez’s lead-taking grand slam in the third inning! 🎙️
0:29

"AN OPPOSITE FIELD GRAND SLAM FOR J.D. MARTINEZ!" Join Gary, Keith, & Ron in the booth for J.D. Martinez’s lead-taking grand slam in the third inning! 🎙️

SNY

85,827 просмотров • 1 год назад

Citi Field rises as Brandon Nimmo blasts a grand slam (Francisco Lindor too in the on-deck circle!)
0:34

Citi Field rises as Brandon Nimmo blasts a grand slam (Francisco Lindor too in the on-deck circle!)

SNY Mets

32,323 просмотров • 1 год назад

OTD in 2018, David Bote hit an ultimate grand slam on Sunday Night Baseball and Wrigley Field was in a FRENZY
0:34

OTD in 2018, David Bote hit an ultimate grand slam on Sunday Night Baseball and Wrigley Field was in a FRENZY

CHGO Cubs

79,967 просмотров • 2 лет назад

As it happened: Huge tornado ripped through a field near Nevada, Iowa. Really scary to see this in real time. WE ARE LIVE -
0:26

As it happened: Huge tornado ripped through a field near Nevada, Iowa. Really scary to see this in real time. WE ARE LIVE -

Max Velocity

44,276 просмотров • 2 лет назад

Imagine hitting a grand slam into the Field of Dreams cornfield 🌽
0:36

Imagine hitting a grand slam into the Field of Dreams cornfield 🌽

Baseball’s Greatest Moments

826,557 просмотров • 1 год назад

SpecNeRF: Gaussian Directional Encoding for Specular Reflections paper page: Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under complex lighting of indoor environments. Unlike existing methods, which typically assume distant lighting like an environment map, we propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Importantly, our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. As a result, it enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients. We further introduce a data-driven geometry prior that helps alleviate the shape radiance ambiguity in reflection modeling. We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.
3:41

SpecNeRF: Gaussian Directional Encoding for Specular Reflections paper page: Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under complex lighting of indoor environments. Unlike existing methods, which typically assume distant lighting like an environment map, we propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Importantly, our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. As a result, it enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients. We further introduce a data-driven geometry prior that helps alleviate the shape radiance ambiguity in reflection modeling. We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.

AK

33,933 просмотров • 2 лет назад

OTD in 2016, Miguel Montero SHOOK Wrigley Field with a pinch-hit grand slam in NLCS Game 1 💪
0:28

OTD in 2016, Miguel Montero SHOOK Wrigley Field with a pinch-hit grand slam in NLCS Game 1 💪

MLB

425,260 просмотров • 8 месяцев назад

SWING AND A DRIVE TOWARD THE GAP IN RIGHT-CENTER; IT'S PRETTY DEEP! IT'S BACK NEAR THE WALL! IT'S GONE! IT'S GONE! FRANCISCO LINDOR! HE MAY HAVE JUST OUTDONE HIMSELF! HE'S HIT A GRAND SLAM INTO THE PHILLIES' BULLPEN IN RIGHT-CENTER FIELD!
0:32

SWING AND A DRIVE TOWARD THE GAP IN RIGHT-CENTER; IT'S PRETTY DEEP! IT'S BACK NEAR THE WALL! IT'S GONE! IT'S GONE! FRANCISCO LINDOR! HE MAY HAVE JUST OUTDONE HIMSELF! HE'S HIT A GRAND SLAM INTO THE PHILLIES' BULLPEN IN RIGHT-CENTER FIELD!

dianna

186,615 просмотров • 7 месяцев назад

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.
0:33

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

AK

122,533 просмотров • 2 лет назад

🗣️ "DEEEEEP LEFT FIELD..." In the PxP booth with Dan Shulman & Buck for Vladdy's GRAND SLAM that sent Rogers Centre into a frenzy! #Postseason
1:19

🗣️ "DEEEEEP LEFT FIELD..." In the PxP booth with Dan Shulman & Buck for Vladdy's GRAND SLAM that sent Rogers Centre into a frenzy! #Postseason

Sportsnet

450,473 просмотров • 9 месяцев назад

The acoustics are pretty amazing. They cranked up AC/DC Hells Bells. Loud. Very clear. Hardly any echo from this spot in end zone near field-level. Can just think about what a game day will sound like. 🔉⬆️
0:42

The acoustics are pretty amazing. They cranked up AC/DC Hells Bells. Loud. Very clear. Hardly any echo from this spot in end zone near field-level. Can just think about what a game day will sound like. 🔉⬆️

Sal Capaccio 🏈

398,706 просмотров • 17 дней назад

Play of the game: Dakota Jordan absolutely DEMOLISHED this baseball, crushing a grand slam 453 feet off the scoreboard in left-center field.
0:31

Play of the game: Dakota Jordan absolutely DEMOLISHED this baseball, crushing a grand slam 453 feet off the scoreboard in left-center field.

San Jose Giants

29,728 просмотров • 1 год назад

Texas A&M EDGE Cashius Howell's "ghost move" coming to an NFL field near you! 👻 𝐶𝑎𝑠ℎ𝑖𝑢𝑠 𝐻𝑜𝑤𝑒𝑙𝑙 | Texas A&M Football | Kay Adams
0:35

Texas A&M EDGE Cashius Howell's "ghost move" coming to an NFL field near you! 👻 𝐶𝑎𝑠ℎ𝑖𝑢𝑠 𝐻𝑜𝑤𝑒𝑙𝑙 | Texas A&M Football | Kay Adams

Up & Adams

177,282 просмотров • 2 месяцев назад