Search Results for author: Tzofi Klinghoffer

Found 12 papers, 4 papers with code

Epi-NAF: Enhancing Neural Attenuation Fields for Limited-Angle CT with Epipolar Consistency Conditions

no code implementations9 Nov 2024 Daniel Gilo, Tzofi Klinghoffer, Or Litany

Neural field methods, initially successful in the inverse rendering domain, have recently been extended to CT reconstruction, marking a paradigm shift from traditional techniques.

CT Reconstruction Inverse Rendering

DISeR: Designing Imaging Systems with Reinforcement Learning

no code implementations ICCV 2023 Tzofi Klinghoffer, Kushagra Tiwary, Nikhil Behari, Bhavya Agrawalla, Ramesh Raskar

In this paper, we formulate these four building blocks of imaging systems as a context-free grammar (CFG), which can be automatically searched over with a learned camera designer to jointly optimize the imaging system with task-specific perception models.

Autonomous Vehicles Depth Estimation +2

Towards Viewpoint Robustness in Bird's Eye View Segmentation

no code implementations ICCV 2023 Tzofi Klinghoffer, Jonah Philion, Wenzheng Chen, Or Litany, Zan Gojcic, Jungseock Joo, Ramesh Raskar, Sanja Fidler, Jose M. Alvarez

We introduce a technique for novel view synthesis and use it to transform collected data to the viewpoint of target rigs, allowing us to train BEV segmentation models for diverse target rigs without any additional data collection or labeling cost.

Autonomous Vehicles Novel View Synthesis

ORCa: Glossy Objects As Radiance-Field Cameras

no code implementations CVPR 2023 Kushagra Tiwary, Akshat Dave, Nikhil Behari, Tzofi Klinghoffer, Ashok Veeraraghavan, Ramesh Raskar

By converting these objects into cameras, we can unlock exciting applications, including imaging beyond the camera's field-of-view and from seemingly impossible vantage points, e. g. from reflections on the human eye.

Novel View Synthesis Object

ORCa: Glossy Objects as Radiance Field Cameras

1 code implementation8 Dec 2022 Kushagra Tiwary, Akshat Dave, Nikhil Behari, Tzofi Klinghoffer, Ashok Veeraraghavan, Ramesh Raskar

By converting these objects into cameras, we can unlock exciting applications, including imaging beyond the camera's field-of-view and from seemingly impossible vantage points, e. g. from reflections on the human eye.

Novel View Synthesis Object

Physically Disentangled Representations

1 code implementation11 Apr 2022 Tzofi Klinghoffer, Kushagra Tiwary, Arkadiusz Balata, Vivek Sharma, Ramesh Raskar

In this paper, we show the utility of inverse rendering in learning representations that yield improved accuracy on downstream clustering, linear classification, and segmentation tasks with the help of our novel Leave-One-Out, Cycle Contrastive loss (LOOCC), which improves disentanglement of scene parameters and robustness to out-of-distribution lighting and viewpoints.

Attribute Classification +3

Towards Learning Neural Representations from Shadows

no code implementations29 Mar 2022 Kushagra Tiwary, Tzofi Klinghoffer, Ramesh Raskar

We observe that shadows are a powerful cue that can constrain neural scene representations to learn SfS, and even outperform NeRF to reconstruct otherwise hidden geometry.

3D Reconstruction Neural Rendering

Self-Supervised Feature Extraction for 3D Axon Segmentation

1 code implementation20 Apr 2020 Tzofi Klinghoffer, Peter Morales, Young-Gyun Park, Nicholas Evans, Kwanghun Chung, Laura J. Brattain

Existing learning-based methods to automatically trace axons in 3D brain imagery often rely on manually annotated segmentation labels.

Segmentation

Feature Forwarding for Efficient Single Image Dehazing

1 code implementation19 Apr 2019 Peter Morales, Tzofi Klinghoffer, Seung Jae Lee

Haze degrades content and obscures information of images, which can negatively impact vision-based decision-making in real-time systems.

Decision Making Decoder +4

Cannot find the paper you are looking for? You can Submit a new open access paper.