Carview!

CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Sun, 04 Aug 2024 16:33:43 GMT access-control-allow-origin: * etag: W/"66afad67-b119" expires: Mon, 29 Dec 2025 04:42:32 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: E0C5:2D64E0:8344F2:93AE14:69520460 accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 04:32:32 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210052-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766982752.312010,VS0,VE205 vary: Accept-Encoding x-fastly-request-id: 9001aaa25a00917fa38f33f65f31bac571ff5d38 content-length: 11663 Despoina Paschalidou

I am a researcher in Computer Vision and Graphics. I am very excited about developing representations that can reliably perceive, capture and recreate the 3D world in a way that humans can interact with it as seamlessly as possible. Throughout the years, I have worked on many exciting problems ranging from 3D reconstruction of objects using interpretable primitive-based representations, generative models for objects, scenes and videos, 3D reconstruction of humans from video data, as well as on several perception tasks such as 3D point cloud reconstruction and segmentation, flow estimation, localization and collision avoidance from egocentric observations. Currently, I am a Senior Research Scientist at the NVIDIA Toronto AI Lab, based in Santa Clara.

Previously, I received my PhD from the Max Planck ETH Center for Learning Systems , where I was advised by Andreas Geiger and Luc van Gool, and I was a Postdoctoral Researcher at Stanford University with Leonidas Guibas. Prior to this, I did my undergraduate in the School of Electrical and Computer Engineering in the Aristotle University of Thessaloniki in Greece, where I worked with Anastasios Delopoulos and Christos Diou. During my PhD, I was very lucky to have spent one wonderful year working with Sanja Fidler at NVIDIA Research, and 6 months at Facebook AI Research, where I worked with David Novotny and Andrea Vedaldi.

Outside of work, I enjoy hiking, skiing, aerial yoga, learning foreign languages (currently I am struggling with Spanish) and cooking!

News

June 2024: I will serve on the program committee for Eurographics 2025!
May 2024: I am an Area Chair for WACV 2025 and 3DV 2025!
May 2024: Received Outstanding Reviewer Award at CVPR 2024!
May 2024:Started a full-time role as a Senior Research Scientist at NVIDIA!
April 2024: We are organizing the 2nd Workshop on AI for 3D Content Creation, the 3D Vision and Modeling Challenges in eCommerce Workshop, the Wild 3D: 3D Modeling, Reconstruction, and Generation in the Wild Workshop and the OpenSUN3D: 3rd Workshop on Open-Vocabulary 3D Scene Understanding Workshop at ECCV 2024 in Milan!!
Feb 2024:Three papers accepted to CVPR 2024! CAD, CurvecloudNet and MultiPhys!
Jan 2024:I am an Area Chair for ECCV 2024!
Dec 2023: We are organizing the 1st Workshop on AI for 3D Generation and the 2nd Workshop on Open-Vocabulary 3D Scene Understanding at CVPR 2024 in Seattle!!
Nov 2023:I am very honored to be one of the EECS Rising Stars 2023!
Jul 2023: Two papers accepted to ICCV 2023! COPILOT and CC3D!
Jun 2023: I am an Area Chair for 3DV 2024 and WACV 2024!
Feb 2023: Two papers accepted to CVPR 2023! PartNeRF and ALTO!
Feb 2022: I started as a Postdoctoral Researcher at Stanford with Prof. Leonidas Guibas!

Selected Publications

CAD: Photorealistic 3D Generation via Adversarial Distillation

Computer Vision and Pattern Recognition (CVPR), 2024

Ziyu Wan, Despoina Paschalidou, Ian Huang, Hongyu Liu, Bokui Shen, Xiaoyu Xiang, Jing Liao, Leonidas Guibas

Abstract Project page Paper Code Video Bibtex

The increased demand for 3D data in AR/VR, robotics and gaming applications, gave rise to powerful generative pipelines capable of synthesizing high-quality 3D objects. Most of these models rely on the Score Distillation Sampling (SDS) algorithm to optimize a 3D representation such that the rendered image maintains a high likelihood as evaluated by a pre-trained diffusion model. However, finding a correct mode in the high-dimensional distribution produced by the diffusion model is challenging and often leads to issues such as over-saturation, over-smoothing, and Janus-like artifacts. In this paper, we propose a novel learning paradigm for 3D synthesis that utilizes pre-trained diffusion models. Instead of focusing on mode-seeking, our method directly models the distribution discrepancy between multi-view renderings and diffusion priors in an adversarial manner, which unlocks the generation of high-fidelity and photorealistic 3D content, conditioned on a single image and prompt. Moreover, by harnessing the latent space of GANs and expressive diffusion model priors, our method facilitates a wide variety of 3D applications including single-view reconstruction, high diversity generation and continuous 3D interpolation in the open domain. The experiments demonstrate the superiority of our pipeline compared to previous works in terms of generation quality and diversity.

@InProceedings{Wan2024CVPR,
      title={CAD: Photorealistic 3d generation via adversarial distillation}, 
      author={Wan, Ziyu and Paschalidou, Despoina and Huang, Ian and Liu, Hongyu and Shen, Bokui and Xiang, Xiaoyu and Liao, Jing and Guibas, Leonidas},
      booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
      year = {2024}
    }

CurveCloudNet: Processing Point Clouds with 1D Structure

Computer Vision and Pattern Recognition (CVPR), 2024

Colton Stearns, Davis Rempe, Alex Fu, Jiateng Liu, Sébastien Mascha, Jeong Joon Park, Despoina Paschalidou, Leonidas Guibas

Abstract Paper Bibtex

Modern depth sensors such as LiDAR operate by sweeping laser-beams across the scene, resulting in a point cloud with notable 1D curve-like structures. In this work, we introduce a new point cloud processing scheme and backbone, called CurveCloudNet, which takes advantage of the curve-like structure inherent to these sensors. While existing backbones discard the rich 1D traversal patterns and rely on generic 3D operations, CurveCloudNet parameterizes the point cloud as a collection of polylines (dubbed a curve cloud), establishing a local surface-aware ordering on the points. By reasoning along curves, CurveCloudNet captures lightweight curve-aware priors to efficiently and accurately reason in several diverse 3D environments. We evaluate CurveCloudNet on multiple synthetic and real datasets that exhibit distinct 3D size and structure. We demonstrate that CurveCloudNet outperforms both point-based and sparse-voxel backbones in various segmentation settings, notably scaling to large scenes better than point-based alternatives while exhibiting improved single-object performance over sparse-voxel alternatives. In all, CurveCloudNet is an efficient and accurate backbone that can handle a larger variety of 3D environments than past works.

@InProceedings{Stearns2024CVPR,
      title={CurveCloudNet: Processing Point Clouds with 1D Structure},
      author={Stearns, Colton and Rempe, Davis and Fu, Alex and Liu, Jiateng and and Masha, Sebastien and Park, Jeong Joon and Paschalidou, Despoina and Guibas, Leonidas J},
      booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
      year = {2024}
    }

CC3D: Layout-Conditioned Generation of Compositional 3D Scenes

International Conference on Computer Vision (ICCV), 2023

Sherwin Bahmani, Jeong Joon Park, Despoina Paschalidou, Xingguang Yan, Gordon Wetzstein, Leonidas Guibas, Andrea Tagliasacchi

Abstract Project page Paper Poster Code Bibtex

In this work, we introduce CC3D, a conditional generative model that synthesizes complex 3D scenes conditioned on 2D semantic scene layouts, trained using single-view images. Different from most existing 3D GANs that limit their applicability to aligned single objects, we focus on generating complex scenes with multiple objects, by modeling the compositional nature of 3D scenes. By devising a 2D layoutbased approach for 3D synthesis and implementing a new 3D field representation with a stronger geometric inductive bias, we have created a 3D GAN that is both efficient and of high quality, while allowing for a more controllable generation process. Our evaluations on synthetic 3D-FRONT and real-world KITTI-360 datasets demonstrate that our model generates scenes of improved visual and geometric quality in comparison to previous works.

@InProceedings{Bahmani2023ICCV,
  author = {Bahmani, Sherwin and Park, Jeong Joon and Paschalidou, Despoina and Yan, Xingguang and Wetzstein, Gordon and Guibas, Leonidas and Tagliasacchi, Andrea},
  title = {CC3D: Layout-Conditioned Generation of Compositional 3D Scenes},
  booktitle = {International Conference on Computer Vision (ICCV)}},
  year = {2023}
}

PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision

Computer Vision and Pattern Recognition (CVPR), 2023

Konstantinos Tertikas, Despoina Paschalidou, Boxiao Pan, Jeong Joon Park, Mikaela Angelina Uy, Ioannis Emiris, Yannis Avrithis, Leonidas Guibas

Abstract Project page Paper Poster Slides Code Video Bibtex

Impressive progress in generative models and implicit representations gave rise to methods that can generate 3D shapes of high quality. However, being able to locally control and edit shapes is another essential property that can unlock several content creation applications. Local control can be achieved with part-aware models, but existing methods require 3D supervision and cannot produce textures. In this work, we devise PartNeRF, a novel part-aware generative model for editable 3D shape synthesis that does not require any explicit 3D supervision. Our model generates objects as a set of locally defined NeRFs, augmented with an affine transformation. This enables several editing operations such as applying transformations on parts, mixing parts from different objects etc. To ensure distinct, manipulable parts we enforce a hard assignment of rays to parts that makes sure that the color of each ray is only determined by a single NeRF. As a result, altering one part does not affect the appearance of the others. Evaluations on various ShapeNet categories demonstrate the ability of our model to generate editable 3D objects of improved fidelity, compared to previous part-based generative approaches that require 3D supervision or models relying on NeRFs.

@InProceedings{Tertikas2023CVPR,
  author    = {Konstantinos Tertikas and Despoina Paschalidou and Boxiao Pan and Jeong Joon Park and Mikaela Angelina Uy and Ioannis Emiris and Yannis Avrithis and Leonidas Guibas},
  title     = {PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision},
  booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2023}
}

ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction

Computer Vision and Pattern Recognition (CVPR), 2023

Zhen Wang, Shijie Zhou, Jeong Joon Park, Despoina Paschalidou, Suya You, Gordon Wetzstein, Leonidas Guibas, Achuta Kadambi

Abstract Project page Paper Poster Slides Code Video Bibtex

This work introduces alternating latent topologies (ALTO) for high-fidelity reconstruction of implicit 3D surfaces from noisy point clouds. Previous work identifies that the spatial arrangement of latent encodings is important to recover detail. One school of thought is to encode a latent vector for each point (point latents). Another school of thought is to project point latents into a grid (grid latents) which could be a voxel grid or triplane grid. Each school of thought has tradeoffs. Grid latents are coarse and lose high-frequency detail. In contrast, point latents preserve detail. However, point latents are more difficult to decode into a surface, and quality and runtime suffer. In this paper, we propose ALTO to sequentially alternate between geometric representations, before converging to an easy-to-decode latent. We find that this preserves spatial expressiveness and makes decoding lightweight. We validate ALTO on implicit 3D recovery and observe not only a performance improvement over the state-of-the-art, but a runtime improvement of 3-10×.

@InProceedings{Zhen2023CVPR,
    title = {ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction},
    author = {Wang, Zhen and Zhou, Shijie and Park, Jeong Joon and Paschalidou, Despoina and You, Suya and Wetzstein, Gordon and Guibas, Leonidas and Kadambi, Achuta},
    booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
    year = {2023}
}

ATISS: Autoregressive Transformers for Indoor Scene Synthesis

Advances in Neural Information Processing Systems (NeurIPS), 2021

Despoina Paschalidou, Amlan Kar, Maria Shugrina, Karsten Kreis, Andreas Geiger, Sanja Fidler

Abstract Project page Paper Poster Slides Code Video Bibtex

The ability to synthesize realistic and diverse indoor furniture layouts automatically or based on partial input, unlocks many applications, from better interactive 3D tools to data synthesis for training and simulation. In this paper, we present ATISS, a novel autoregressive transformer architecture for creating diverse and plausible synthetic indoor environments, given only the room type and its floor plan. In contrast to prior work, which poses scene synthesis as sequence generation, our model generates rooms as unordered sets of objects. We argue that this formulation is more natural, as it makes ATISS generally useful beyond fully automatic room layout synthesis. For example, the same trained model can be used in interactive applications for general scene completion, partial room re-arrangement with any objects specified by the user, as well as object suggestions for any partial room. To enable this, our model leverages the permutation equivariance of the transformer when conditioning on the partial scene, and is trained to be permutation-invariant across object orderings. Our model is trained end-to-end as an autoregressive generative model using only labeled 3D bounding boxes as supervision. Evaluations on four room types in the 3D-FRONT dataset demonstrate that our model consistently generates plausible room layouts that are more realistic than existing methods. In addition, it has fewer parameters, is simpler to implement and train and runs up to 8x faster than existing methods.

@InProceedings{Paschalidou2021NEURIPS,
  author = {Despoina Paschalidou and Amlan Kar and Maria Shugrina and Karsten Kreis and Andreas Geiger and Sanja Fidler},
  title = {ATISS: Autoregressive Transformers for Indoor Scene Synthesis},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021}
}

Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks

Computer Vision and Pattern Recognition (CVPR), 2021

Despoina Paschalidou, Angelos Katharopoulos, Andreas Geiger, Sanja Fidler

Abstract Project page Paper Poster Code Blog Slides Video Podcast Bibtex

Impressive progress in 3D shape extraction led to representations that can capture object geometries with high fidelity. In parallel, primitive-based methods seek to represent objects as semantically consistent part arrangements. However, due to the simplicity of existing primitive representations, these methods fail to accurately reconstruct 3D shapes using a small number of primitives/parts. We address the trade-off between reconstruction quality and number of parts with Neural Parts, a novel 3D primitive representation that defines primitives using an Invertible Neural Network (INN) which implements homeomorphic mappings between a sphere and the target object. The INN allows us to compute the inverse mapping of the homeomorphism, which in turn, enables the efficient computation of both the implicit surface function of a primitive and its mesh, without any additional post-processing. Our model learns to parse 3D objects into semantically consistent part arrangements without any part-level supervision. Evaluations on ShapeNet, D-FAUST and FreiHAND demonstrate that our primitives can capture complex geometries and thus simultaneously achieve geometrically accurate as well as interpretable reconstructions using an order of magnitude fewer primitives than state-of-the-art shape abstraction methods.

@InProceedings{Paschalidou2021CVPR,
    title = {Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks},
    author = {Paschalidou, Despoina and Katharopoulos, Angelos and Geiger, Andreas and Fidler, Sanja},
    booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
    month = jun,
    year = {2021}
}

Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image

Computer Vision and Pattern Recognition (CVPR), 2020

Despoina Paschalidou, Luc van Gool, Andreas Geiger

Abstract Project page Paper Poster Code Blog Slides Video Bibtex

Humans perceive the 3D world as a set of distinct objects that are characterized by various low-level (geometry, reflectance) and high-level (connectivity, adjacency, symmetry) properties. Recent methods based on convolutional neural networks (CNNs) demonstrated impressive progress in 3D reconstruction, even when using a single 2D image as input. However, the majority of these methods focuses on recovering the local 3D geometry of an object without considering its part-based decomposition or relations between parts. We address this challenging problem by proposing a novel formulation that allows to jointly recover the geometry of a 3D object as a set of primitives as well as their latent hierarchical structure without part-level supervision. Our model recovers the higher level structural decomposition of various objects in the form of a binary tree of primitives, where simple parts are represented with fewer primitives and more complex parts are modeled with more components. Our experiments on the ShapeNet and D-FAUST datasets demonstrate that considering the organization of parts indeed facilitates reasoning about 3D geometry.

@InProceedings{Paschalidou2020CVPR,
    title = {Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image},
    author = {Paschalidou, Despoina and Luc van Gool and Geiger, Andreas},
    booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
    month = jun,
    year = {2020},
}

Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids

Computer Vision and Pattern Recognition (CVPR), 2019

Despoina Paschalidou, Ali Osman Ulusoy, Andreas Geiger

Abstract Project page Paper Poster Code Blog Video Bibtex

Abstracting complex 3D shapes with parsimonious part-based representations has been a long standing goal in computer vision. This paper presents a learning-based solution to this problem which goes beyond the traditional 3D cuboid representation by exploiting superquadrics as atomic elements. We demonstrate that superquadrics lead to more expressive 3D scene parses while being easier to learn than 3D cuboid representations. Moreover, we provide an analytical solution to the Chamfer loss which avoids the need for computational expensive reinforcement learning or iterative prediction. Our model learns to parse 3D objects into consistent superquadric representations without supervision. Results on various ShapeNet categories as well as the SURREAL human body dataset demonstrate the flexibility of our model in capturing fine details and complex poses that could not have been modelled using cuboids.

@InProceedings{Paschalidou2019CVPR,
    title = {Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids},
    author = {Paschalidou, Despoina and Ulusoy, Ali Osman and Geiger, Andreas},
    booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
    month = jun,
    year = {2019},
}

Original Source | Taken Source