Search Results for author: Sergey Zakharov

Found 26 papers, 6 papers with code

Zero-Shot Multi-Object Shape Completion

no code implementations21 Mar 2024 Shun Iwase, Katherine Liu, Vitor Guizilini, Adrien Gaidon, Kris Kitani, Rares Ambrus, Sergey Zakharov

We present a 3D shape completion method that recovers the complete geometry of multiple objects in complex scenes from a single RGB-D image.


FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects

no code implementations19 Oct 2023 Mayank Lunayach, Sergey Zakharov, Dian Chen, Rares Ambrus, Zsolt Kira, Muhammad Zubair Irshad

In this work, we address the challenging task of 3D object recognition without the reliance on real-world 3D labeled data.

3D Object Recognition 6D Pose Estimation

NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes

1 code implementation ICCV 2023 Muhammad Zubair Irshad, Sergey Zakharov, Katherine Liu, Vitor Guizilini, Thomas Kollar, Adrien Gaidon, Zsolt Kira, Rares Ambrus

NeO 360's representation allows us to learn from a large collection of unbounded 3D scenes while offering generalizability to new views and novel scenes from as few as a single image during inference.

Generalizable Novel View Synthesis Novel View Synthesis

DeLiRa: Self-Supervised Depth, Light, and Radiance Fields

no code implementations ICCV 2023 Vitor Guizilini, Igor Vasiljevic, Jiading Fang, Rares Ambrus, Sergey Zakharov, Vincent Sitzmann, Adrien Gaidon

In this work, we propose to use the multi-view photometric objective from the self-supervised depth estimation literature as a geometric regularizer for volumetric rendering, significantly improving novel view synthesis without requiring additional information.

3D Reconstruction Depth Estimation +1

Zero-1-to-3: Zero-shot One Image to 3D Object

1 code implementation ICCV 2023 Ruoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov, Sergey Zakharov, Carl Vondrick

We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image.

3D Reconstruction Image to 3D +3

ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapes

no code implementations12 Dec 2022 Sergey Zakharov, Rares Ambrus, Katherine Liu, Adrien Gaidon

Compact and accurate representations of 3D shapes are central to many perception and robotics tasks.


Photo-realistic Neural Domain Randomization

no code implementations23 Oct 2022 Sergey Zakharov, Rares Ambrus, Vitor Guizilini, Wadim Kehl, Adrien Gaidon

In this paper, we show that the recent progress in neural rendering enables a new unified approach we call Photo-realistic Neural Domain Randomization (PNDR).

Image Generation Monocular Depth Estimation +3

Neural Groundplans: Persistent Neural Scene Representations from a Single Image

no code implementations22 Jul 2022 Prafull Sharma, Ayush Tewari, Yilun Du, Sergey Zakharov, Rares Ambrus, Adrien Gaidon, William T. Freeman, Fredo Durand, Joshua B. Tenenbaum, Vincent Sitzmann

We present a method to map 2D image observations of a scene to a persistent 3D scene representation, enabling novel view synthesis and disentangled representation of the movable and immovable components of the scene.

Disentanglement Instance Segmentation +4

SpOT: Spatiotemporal Modeling for 3D Object Tracking

no code implementations12 Jul 2022 Colton Stearns, Davis Rempe, Jie Li, Rares Ambrus, Sergey Zakharov, Vitor Guizilini, Yanchao Yang, Leonidas J Guibas

In this work, we develop a holistic representation of traffic scenes that leverages both spatial and temporal information of the actors in the scene.

3D Multi-Object Tracking 3D Object Tracking +1

Multi-View Object Pose Refinement With Differentiable Renderer

no code implementations6 Jul 2022 Ivan Shugurov, Ivan Pavlov, Sergey Zakharov, Slobodan Ilic

This paper introduces a novel multi-view 6 DoF object pose refinement approach focusing on improving methods trained on synthetic data.

Camera Calibration Object

DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation

no code implementations6 Jul 2022 Ivan Shugurov, Sergey Zakharov, Slobodan Ilic

The main conclusions is that RGB excels in correspondence estimation, while depth contributes to the pose accuracy if good 3D-3D correspondences are available.

Object object-detection +2

Unsupervised Discovery and Composition of Object Light Fields

no code implementations8 May 2022 Cameron Smith, Hong-Xing Yu, Sergey Zakharov, Fredo Durand, Joshua B. Tenenbaum, Jiajun Wu, Vincent Sitzmann

Neural scene representations, both continuous and discrete, have recently emerged as a powerful new paradigm for 3D scene understanding.

Novel View Synthesis Object +1

Multi-Frame Self-Supervised Depth with Transformers

no code implementations CVPR 2022 Vitor Guizilini, Rares Ambrus, Dian Chen, Sergey Zakharov, Adrien Gaidon

Experiments on the KITTI and DDAD datasets show that our DepthFormer architecture establishes a new state of the art in self-supervised monocular depth estimation, and is even competitive with highly specialized supervised single-frame architectures.

Monocular Depth Estimation

Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors

1 code implementation CVPR 2020 Sergey Zakharov, Wadim Kehl, Arjun Bhargava, Adrien Gaidon

We present an automatic annotation pipeline to recover 9D cuboids and 3D shapes from pre-trained off-the-shelf 2D detectors and sparse LIDAR data.

3D Object Instance Recognition and Pose Estimation Using Triplet Loss with Dynamic Margin

no code implementations9 Apr 2019 Sergey Zakharov, Wadim Kehl, Benjamin Planche, Andreas Hutter, Slobodan Ilic

In this paper, we address the problem of 3D object instance recognition and pose estimation of localized objects in cluttered environments using convolutional neural networks.

Pose Estimation

HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects

no code implementations5 Apr 2019 Roman Kaskman, Sergey Zakharov, Ivan Shugurov, Slobodan Ilic

We also present a set of benchmarks to test various desired detector properties, particularly focusing on scalability with respect to the number of objects and resistance to changing light conditions, occlusions and clutter.

6D Pose Estimation 6D Pose Estimation using RGB +1

DPOD: 6D Pose Object Detector and Refiner

2 code implementations ICCV 2019 Sergey Zakharov, Ivan Shugurov, Slobodan Ilic

An additional RGB pose refinement of the initial pose estimates is performed using a custom deep learning-based refinement scheme.

3D Object Detection 6D Pose Estimation +3

Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition

no code implementations9 Oct 2018 Benjamin Planche, Sergey Zakharov, Ziyan Wu, Andreas Hutter, Harald Kosch, Slobodan Ilic

Applying our approach to object recognition from texture-less CAD data, we present a custom generative network which fully utilizes the purely geometrical information to learn robust features and achieve a more refined mapping for unseen color images.

Denoising Domain Adaptation +1

When Regression Meets Manifold Learning for Object Recognition and Pose Estimation

no code implementations16 May 2018 Mai Bui, Sergey Zakharov, Shadi Albarqouni, Slobodan Ilic, Nassir Navab

By combining the strengths of manifold learning using triplet loss and pose regression, we could either estimate the pose directly reducing the complexity compared to NN search, or use learned descriptor for the NN descriptor matching.

Multi-Task Learning Object Recognition +4

Keep it Unreal: Bridging the Realism Gap for 2.5D Recognition with Geometry Priors Only

no code implementations24 Apr 2018 Sergey Zakharov, Benjamin Planche, Ziyan Wu, Andreas Hutter, Harald Kosch, Slobodan Ilic

With the increasing availability of large databases of 3D CAD models, depth-based recognition methods can be trained on an uncountable number of synthetically rendered images.

Generative Adversarial Network

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