Sergey Zakharov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sergey Zakharov has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Rares Ambrus
Toyota Research Institute, Cambridge, MA 02139, USA
5 shared publications - Adrien Gaidon
Toyota Research Institute
3 shared publications - Vitor Guizilini
Toyota Research Institute
3 shared publications - Muhammad Zubair Irshad
Toyota Research Institute
2 shared publications - Zsolt Kira
Georgia Institute of Technology
2 shared publications Adrien Gaidon
Toyota Research Institute
1 shared publication
Latest Publications
- Open Access
- 19 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-5
A Multi-flash Stereo Camera for Photo-realistic Capture of Small Scenes
- 19 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessA Multi-flash Stereo Camera for Photo-realistic Capture of Small Scenes
- Open Access
$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation
Incorporating inductive bias by embedding geometric entities (such as rays) as input has proven successful in multi-view learning. However, the methods adopting this technique typically lack equivariance, which is crucial for effective 3D learning. Equivariance serves as a valuable inductive prior, aiding in the generation of robust multi-view features for 3D scene understanding. In this paper, we explore the application of equivariant multi-view learning to depth estimation, not only recognizing its significance for computer vision and robotics but also addressing the limitations of previous research. Most prior studies have either overlooked equivariance in this setting or achieved only approximate equivariance through data augmentation, which often leads to inconsistencies across different reference frames. To address this issue, we propose to embed $SE(3)$ equivariance into the Perceiver IO architecture. We employ Spherical Harmonics for positional encoding to ensure 3D rotation equivariance, and develop a specialized equivariant encoder and decoder within the Perceiver IO architecture. To validate our model, we applied it to the task of stereo depth estimation, achieving state of the art results on real-world datasets without explicit geometric constraints or extensive data augmentation.Open Access$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation
Incorporating inductive bias by embedding geometric entities (such as rays) as input has proven successful in multi-view learning. However, the methods adopting this technique typically lack equivariance, which is crucial for effective 3D learning. Equivariance serves as a valuable inductive prior, aiding in the generation of robust multi-view features for 3D scene understanding. In this paper, we explore the application of equivariant multi-view learning to depth estimation, not only recognizing its significance for computer vision and robotics but also addressing the limitations of previous research. Most prior studies have either overlooked equivariance in this setting or achieved only approximate equivariance through data augmentation, which often leads to inconsistencies across different reference frames. To address this issue, we propose to embed $SE(3)$ equivariance into the Perceiver IO architecture. We employ Spherical Harmonics for positional encoding to ensure 3D rotation equivariance, and develop a specialized equivariant encoder and decoder within the Perceiver IO architecture. To validate our model, we applied it to the task of stereo depth estimation, achieving state of the art results on real-world datasets without explicit geometric constraints or extensive data augmentation. - 8 November 2024
- Published by Springer Nature
- p. 434-453
NeRF-MAE: Masked AutoEncoders for Self-supervised 3D Representation Learning for Neural Radiance Fields
- 8 November 2024
- Published by Springer Nature
- p. 434-453
NeRF-MAE: Masked AutoEncoders for Self-supervised 3D Representation Learning for Neural Radiance Fields
- Open Access
- 13 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
ReFiNe: Recursive Field Networks for Cross-Modal Multi-Scene Representation
The common trade-offs of state-of-the-art methods for multi-shape representation (a single model "packing" multiple objects) involve trading modeling accuracy against memory and storage. We show how to encode multiple shapes represented as continuous neural fields with a higher degree of precision than previously possible and with low memory usage. Key to our approach is a recursive hierarchical formulation that exploits object self-similarity, leading to a highly compressed and efficient shape latent space. Thanks to the recursive formulation, our method supports spatial and global-to-local latent feature fusion without needing to initialize and maintain auxiliary data structures, while still allowing for continuous field queries to enable applications such as raytracing. In experiments on a set of diverse datasets, we provide compelling qualitative results and demonstrate state-of-the-art multi-scene reconstruction and compression results with a single network per dataset.
- 13 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessReFiNe: Recursive Field Networks for Cross-Modal Multi-Scene Representation
The common trade-offs of state-of-the-art methods for multi-shape representation (a single model "packing" multiple objects) involve trading modeling accuracy against memory and storage. We show how to encode multiple shapes represented as continuous neural fields with a higher degree of precision than previously possible and with low memory usage. Key to our approach is a recursive hierarchical formulation that exploits object self-similarity, leading to a highly compressed and efficient shape latent space. Thanks to the recursive formulation, our method supports spatial and global-to-local latent feature fusion without needing to initialize and maintain auxiliary data structures, while still allowing for continuous field queries to enable applications such as raytracing. In experiments on a set of diverse datasets, we provide compelling qualitative results and demonstrate state-of-the-art multi-scene reconstruction and compression results with a single network per dataset.
- 11 November 2022
- Published by Springer Nature
- p. 275-292
ShAPO: Implicit Representations for Multi-object Shape, Appearance, and Pose Optimization
- 11 November 2022
- Published by Springer Nature
- p. 275-292
ShAPO: Implicit Representations for Multi-object Shape, Appearance, and Pose Optimization