Search Results for author:
Found 65 papers, 28 papers with code
Towards Precise Completion of Deformable Shapes
Here, we claim that observing part of an object which was previously acquired as a whole, one could deal with both partial matching and shape completion in a holistic manner.
Robust Symmetry Detection via Riemannian Langevin Dynamics
In contrast, learning-based methods may be more robust to noise, but often overlook partial symmetries due to the scarcity of annotated data.
OmniRe: Omni Urban Scene Reconstruction
To that end, we propose a comprehensive 3DGS framework for driving scenes, named OmniRe, that allows for accurate, full-length reconstruction of diverse dynamic objects in a driving log.
Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering
Generating realistic images from arbitrary views based on a single source image remains a significant challenge in computer vision, with broad applications ranging from e-commerce to immersive virtual experiences.
The NeRFect Match: Exploring NeRF Features for Visual Localization
Significantly, we introduce NeRFMatch, an advanced 2D-3D matching function that capitalizes on the internal knowledge of NeRF learned via view synthesis.
OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding
This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023.
Approximately Piecewise E(3) Equivariant Point Networks
Integrating a notion of symmetry into point cloud neural networks is a provably effective way to improve their generalization capability.
Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation
To generate composite animations from a multi-track timeline, we propose a new test-time denoising method.
Dynamic LiDAR Re-simulation using Compositional Neural Fields
We introduce DyNFL, a novel neural field-based approach for high-fidelity re-simulation of LiDAR scans in dynamic driving scenes.
3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features
However, these features are initially trained on paired text and image data, which are not optimized for 3D tasks, and often exhibit a domain gap when applied to the target data.
EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
We present EmerNeRF, a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes.
Towards Viewpoint Robustness in Bird's Eye View Segmentation
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.
Semi-Supervised Semantic Segmentation via Marginal Contextual Information
We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation.
Neural Kernel Surface Reconstruction
We present a novel method for reconstructing a 3D implicit surface from a large-scale, sparse, and noisy point cloud.
Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids
To apply this representation to monocular scene reconstruction, we develop a scale calibration algorithm for fast geometric initialization from monocular depth priors.
Neural LiDAR Fields for Novel View Synthesis
We present Neural Fields for LiDAR (NFL), a method to optimise a neural field scene representation from LiDAR measurements, with the goal of synthesizing realistic LiDAR scans from novel viewpoints.
Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion
We introduce a method for generating realistic pedestrian trajectories and full-body animations that can be controlled to meet user-defined goals.
UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes
We propose UnScene3D, the first fully unsupervised 3D learning approach for class-agnostic 3D instance segmentation of indoor scans.
LION: Latent Point Diffusion Models for 3D Shape Generation
To advance 3D DDMs and make them useful for digital artists, we require (i) high generation quality, (ii) flexibility for manipulation and applications such as conditional synthesis and shape interpolation, and (iii) the ability to output smooth surfaces or meshes.
Ranked #1 on
Point Cloud Generation
on ShapeNet Airplane
Mask3D: Mask Transformer for 3D Semantic Instance Segmentation
Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques.
Ranked #1 on
3D Instance Segmentation
on STPLS3D
3D Instance Segmentation
3D Semantic Instance Segmentation
+2
GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images
As several industries are moving towards modeling massive 3D virtual worlds, the need for content creation tools that can scale in terms of the quantity, quality, and diversity of 3D content is becoming evident.
MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation
As a result, the learned 2D representations are view-invariant and geometrically consistent, leading to better generalization when trained on a limited number of labeled shapes compared to alternatives that utilize self-supervision in 2D or 3D alone.
Language-Grounded Indoor 3D Semantic Segmentation in the Wild
Recent advances in 3D semantic segmentation with deep neural networks have shown remarkable success, with rapid performance increase on available datasets.
Ranked #7 on
3D Semantic Segmentation
on ScanNet200
Learning Smooth Neural Functions via Lipschitz Regularization
The latent descriptor of a neural field acts as a deformation handle for the 3D shape it represents.
Causal Scene BERT: Improving object detection by searching for challenging groups of data
Our main contribution is a pseudo-automatic method to discover such groups in foresight by performing causal interventions on simulated scenes.
Federated Learning with Heterogeneous Architectures using Graph HyperNetworks
Standard Federated Learning (FL) techniques are limited to clients with identical network architectures.
Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior
Scenario generation is formulated as an optimization in the latent space of this traffic model, perturbing an initial real-world scene to produce trajectories that collide with a given planner.
Neural Fields as Learnable Kernels for 3D Reconstruction
We present Neural Kernel Fields: a novel method for reconstructing implicit 3D shapes based on a learned kernel ridge regression.
Neural Fields in Visual Computing and Beyond
Recent advances in machine learning have created increasing interest in solving visual computing problems using a class of coordinate-based neural networks that parametrize physical properties of scenes or objects across space and time.
DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer
We consider the challenging problem of predicting intrinsic object properties from a single image by exploiting differentiable renderers.
Mix3D: Out-of-Context Data Augmentation for 3D Scenes
Since scene context helps reasoning about object semantics, current works focus on models with large capacity and receptive fields that can fully capture the global context of an input 3D scene.
Ranked #20 on
Semantic Segmentation
on ScanNet
Causal Scene BERT: Improving object detection by searching for challenging groups
We verify that the prioritized groups found via intervention are challenging for the object detector and show that retraining with data collected from these groups helps inordinately compared to adding more IID data.
StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects
We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more unposed RGB images.
Vector Neurons: A General Framework for SO(3)-Equivariant Networks
Invariance and equivariance to the rotation group have been widely discussed in the 3D deep learning community for pointclouds.
Learning Spectral Unions of Partial Deformable 3D Shapes
Spectral geometric methods have brought revolutionary changes to the field of geometry processing.
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
In this paper, we identify a "warm-up obstacle": the inability of standard warm-up stages to train high quality feature extractors and avert memorization of noisy labels.
Ranked #1 on
Image Classification
on CIFAR-10 (with noisy labels)
Weakly Supervised Learning of Rigid 3D Scene Flow
We propose a data-driven scene flow estimation algorithm exploiting the observation that many 3D scenes can be explained by a collection of agents moving as rigid bodies.
Self-Supervised Equivariant Scene Synthesis from Video
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into background, characters, and their animations.
Human 3D keypoints via spatial uncertainty modeling
We introduce a technique for 3D human keypoint estimation that directly models the notion of spatial uncertainty of a keypoint.
3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection
On KITTI, we are the first to demonstrate semi-supervised 3D object detection and our method surpasses a fully supervised baseline from 1. 8% to 7. 6% under different label ratios and categories.
Non-Rigid Puzzles
We assume to be given a reference shape and its multiple parts undergoing a non-rigid deformation.
Learned Equivariant Rendering without Transformation Supervision
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background.
ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation
To validate our method, we apply ReLMoGen to two types of tasks: 1) Interactive Navigation tasks, navigation problems where interactions with the environment are required to reach the destination, and 2) Mobile Manipulation tasks, manipulation tasks that require moving the robot base.
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
To this end, we select a suite of diverse datasets and tasks to measure the effect of unsupervised pre-training on a large source set of 3D scenes.
Object-Centric Multi-View Aggregation
We present an approach for aggregating a sparse set of views of an object in order to compute a semi-implicit 3D representation in the form of a volumetric feature grid.
Representation Learning Through Latent Canonicalizations
We seek to learn a representation on a large annotated data source that generalizes to a target domain using limited new supervision.
On Learning Sets of Symmetric Elements
We first characterize the space of linear layers that are equivariant both to element reordering and to the inherent symmetries of elements, like translation in the case of images.
Continuous Geodesic Convolutions for Learning on 3D Shapes
In this work, we wish to challenge this practice and use a neural network to learn descriptors directly from the raw mesh.
ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes
Compared to prior work on multi-modal detection, we explicitly extract both geometric and semantic features from the 2D images.
Ranked #2 on
3D Object Detection
on SUN-RGBD
(using extra training data)
The Whole Is Greater Than the Sum of Its Nonrigid Parts
Here, we claim that observing part of an object which was previously acquired as a whole, one could deal with both partial matching and shape completion in a holistic manner.
Deep Hough Voting for 3D Object Detection in Point Clouds
Current 3D object detection methods are heavily influenced by 2D detectors.
3D Object Detection
3D Object Detection From Monocular Images
+2
Self-supervised Learning of Dense Shape Correspondence
The resulting learning model is class-agnostic, and is able to leverage any type of deformable geometric data for the training phase.
Class-Aware Fully-Convolutional Gaussian and Poisson Denoising
We propose a fully-convolutional neural-network architecture for image denoising which is simple yet powerful.
Dual-Primal Graph Convolutional Networks
In recent years, there has been a surge of interest in developing deep learning methods for non-Euclidean structured data such as graphs.
SOSELETO: A Unified Approach to Transfer Learning and Training with Noisy Labels
We present SOSELETO (SOurce SELEction for Target Optimization), a new method for exploiting a source dataset to solve a classification problem on a target dataset.
Deformable Shape Completion with Graph Convolutional Autoencoders
In this work, we propose a novel learning-based method for the completion of partial shapes.
Efficient Deformable Shape Correspondence via Kernel Matching
We present a method to match three dimensional shapes under non-isometric deformations, topology changes and partiality.
Deep Functional Maps: Structured Prediction for Dense Shape Correspondence
We introduce a new framework for learning dense correspondence between deformable 3D shapes.
Deep Class Aware Denoising
We further show that a significant boost in performance of up to $0. 4$ dB PSNR can be achieved by making our network class-aware, namely, by fine-tuning it for images belonging to a specific semantic class.
Deep Convolutional Denoising of Low-Light Images
Poisson distribution is used for modeling noise in photon-limited imaging.
Cloud Dictionary: Sparse Coding and Modeling for Point Clouds
With the development of range sensors such as LIDAR and time-of-flight cameras, 3D point cloud scans have become ubiquitous in computer vision applications, the most prominent ones being gesture recognition and autonomous driving.
FPGA system for real-time computational extended depth of field imaging using phase aperture coding
We present a proof-of-concept end-to-end system for computational extended depth of field (EDOF) imaging.
Image reconstruction from dense binary pixels
Recently, the dense binary pixel Gigavision camera had been introduced, emulating a digital version of the photographic film.
ASIST: Automatic Semantically Invariant Scene Transformation
We present ASIST, a technique for transforming point clouds by replacing objects with their semantically equivalent counterparts.
A Picture is Worth a Billion Bits: Real-Time Image Reconstruction from Dense Binary Pixels
In this work, we study a variant of a sensor with binary threshold pixels and propose a reconstruction algorithm combining an ML data fitting term with a sparse synthesis prior.
