Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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

Roni Sengupta

2,610 subscribers

19,439 views • 1 year ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

2 Comments

Roni Sengupta1 year ago

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.

Virtue of Selfish Investing (VoSI)2 years ago

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.

Related Videos

🚀 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.

🚀 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 views • 11 months ago

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

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

AK

36,140 views • 3 years ago

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.”

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 views • 2 years ago

Grand slam on division 1 field!

Grand slam on division 1 field!

Andy Beshear

97,812 views • 1 year ago

"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! 🎙️

"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 views • 2 years ago

Grounded API is live. - SOTA on hand-tracking benchmarks (< 1 cm) - SOTA on SLAM benchmarks - In-the-wild ego data -> enriched data in minutes - Integration with Hugging Face LeRobot & Rerun - Built for BitRobot 🦾 RoboCap suite Technical report & more↓

Grounded API is live. - SOTA on hand-tracking benchmarks (< 1 cm) - SOTA on SLAM benchmarks - In-the-wild ego data -> enriched data in minutes - Integration with Hugging Face LeRobot & Rerun - Built for BitRobot 🦾 RoboCap suite Technical report & more↓

Grounded Superintelligence

175,999 views • 1 month ago

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

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

CHGO Cubs

79,979 views • 3 years ago

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

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

44,299 views • 2 years ago

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

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

Baseball’s Greatest Moments

827,045 views • 1 year ago

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.

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

33,948 views • 2 years ago

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

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

MLB

427,779 views • 1 year ago

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!

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

186,645 views • 11 months ago

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.

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

122,567 views • 3 years ago

WALK-OFF GRAND SLAM! With the bases loaded in the 7th inning, Isaac Pegors broke a scoreless tie with a grand slam to straightaway center field! UMARY Baseball #LifeAtMary #ForTheShip

WALK-OFF GRAND SLAM! With the bases loaded in the 7th inning, Isaac Pegors broke a scoreless tie with a grand slam to straightaway center field! UMARY Baseball #LifeAtMary #ForTheShip

UMary Marauders

18,094 views • 1 year ago

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

🗣️ "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

450,735 views • 1 year ago